Skip to content

GitLab

Commit b309ea1b authored by chenzk's avatar chenzk
Browse files

v1.0

parents
Hide whitespace changes
Inline Side-by-side
Showing with 1709 additions and 0 deletions
text/langdetect/profiles/ur 0 → 100644
View file @ b309ea1b
{"freq":{"ٹ":7565,"پ":19909,"ٰ":348,"و":91887,"ي":164757,"ً":561,"َ":343,"ُ":600,"ـ":316,"ف":15396,"ق":19382,"ك":314,"ل":61015,"م":85213,"ن":73500,"ه":210,"ّ":218,"ِ":1208,"خ":10520,"د":42999,"ج":29799,"ح":15399,"ت":63424,"ث":2772,"ب":46160,"ئ":12622,"ا":210246,"ؤ":741,"آ":6835,"ء":3457,"غ":3607,"ع":26594,"ظ":4173,"ط":9560,"ض":4853,"ص":11646,"ش":17043,"س":59068,"ز":13283,"ر":100269,"ذ":2393,"،":8584,"؛":310,"ہ":81948,"ۃ":194,"ۂ":442,"ے":72723,"ۓ":1226,"۔":21285,"گ":13942,"ک":96247,"ھ":18217,"ں":33709,"چ":6431,"ڈ":3486,"ڑ":2986,"ژ":212," ،":2410," ۔":1318," ہ":33487," ھ":395," گ":5518," ک":67994," ن":12353," ل":8072," م":43729," ق":5408," ك":206," ف":4429," ي":9396," و":11189," ص":3954," ش":8375," ط":3503," ض":1387," ر":7523," ذ":1057," س":22509," ز":3628," ع":9286," ظ":270," غ":946," ا":57235," ء":2548," آ":6281," ج":19940," ح":6228," خ":5235," د":11120," ب":20334," ت":17083," ث":374," چ":3475," ڈ":1133," ٹ":932," پ":14925,"کا ":9732,"کت ":188," ، ":2340," ء ":2420," و ":1367," بھ":3806," جن":2286," حا":1179," جل":205," بہ":901," جم":727," جي":597," جو":3440," جد":255," جس":2699," جز":358," جر":340," اے":201," اہ":629," جا":6670," جب":836," تي":855," اک":704," بڑ":974," اگ":491," خل":943," تہ":199," تھ":4319," خي":280," خو":966," دا":1316," خص":169," خر":184," خد":283," خط":402," حق":234," حي":633," تک":1112," حم":243," خا":1564," حر":509," حس":437," حد":214," حض":717," حص":647," بے":210," بن":2795," بل":1071," بغ":190," بع":1385," اُ":270," بر":1803," اي":8027," او":11360," بد":254," بح":524," اق":467," اف":961," ال":4248," با":2739," ان":6816," ام":1333," اط":314," اع":876," اد":879," ار":1330," از":241," اس":10716," اش":424," اص":842," اض":219," اب":1381," ات":313," اث":175," اج":297," اح":507," اخ":805," تو":1190," بچ":211," تن":378," تم":482," تق":681," تف":194," تع":1588," تش":261," تص":444," تر":1553," تخ":375," تج":367," تح":884," تا":1192," تب":411," اپ":1467," اٹ":312," بو":485," بي":1555," آپ":775," آل":254," آن":292," آي":279," آخ":168," آر":246," آت":368," آج":212," آئ":402," آب":1319," آف":180," آس":249," آز":331," عہ":219," سے":9513," شک":419," طو":1200," ظا":186," عظ":314," عر":1083," عد":298," عث":218," عا":1056," عب":533," شہ":1939," عي":293," عل":2998," عم":1153," عن":249," عو":213," غي":270," سع":194," سط":261," دھ":223," سف":224," سي":1366," سو":980," سم":787," دہ":248," شا":2109," سن":832," سل":1069," شر":734," شخ":260," شع":372," شي":299," شم":1497," صا":255," صر":324," رک":1032," صح":380," صد":878," صل":252," صف":254," صو":1376," رہ":1328," ضر":190," ضل":1004," طا":301," طب":638," سک":803," طر":1051," دس":404," در":2025," دي":2436," دو":2534," دن":789," دل":217," ذر":344," جگ":269," حک":746," ذي":205," جہ":593," را":903," جھ":293," رس":334," ري":940," زر":261," رق":405," رو":1485," زب":1015," زا":201," رن":190," زي":935," سر":1466," زم":612," سب":960," سا":2953," زن":311," ست":266,"گھر":200,"گہ ":210," ہے":16945,"گوں":240,"گيا":1207," ٹا":182," پڑ":329," پن":536," پو":662," پي":2142," پا":3033," پت":168," پر":5135," پش":170," پس":187," ٹي":317," لف":878,"ں، ":508," لغ":168," لح":265," لئ":237," لا":1034," مل":1468," مق":1520," مف":313," مغ":611," مع":1708," مط":921," مض":238," مص":513," مس":1572," مش":1902," مر":2119," مز":309," مد":642," مذ":261," مح":1355," مخ":914," لي":2681," مث":406," مج":498," لو":614," مت":1246," ما":1837," نف":215," نق":288," نم":568," نظ":923," نس":373," نش":178," مم":601," من":1456," نا":2714," نب":179," مو":1833," مي":17546," نج":183," وا":3957," لڑ":168," نو":730," ني":646," فض":168," فر":1011," فا":763," فت":168," قس":291," قص":318," فل":520," قا":1019," فن":193," فو":398," قب":691," في":493," قد":579," قر":855," فٹ":171," قل":240," قو":565," قي":355," وہ":1582," يہ":4254," لک":550," وج":661," لگ":411," وس":430," وز":353," ور":376," وغ":293," ول":235," وق":563," وف":272," مک":558," وي":428," لے":206," مگ":362," مہ":365," يا":2941," نک":275," نگ":248," يع":665," نہ":1220," يو":1100," نے":2696," گھ":362," ہو":7614," ہم":409," ہن":745," ہي":5912," ہز":243," ہر":384," ہا":430," ہج":240," کت":582," کر":5496," کس":1214," کش":187," کل":1235," کن":341," کم":719," کو":6421," کي":15836," کا":11009," کئ":348," کہ":5408," کھ":713," گا":490," گئ":863," کے":17634," کچ":321," گن":214," گل":202," گي":1388," گو":519," گر":807," ۔ ":1018," پہ":1353," پھ":659," چت":240," چا":498," چل":252," چي":492," چو":467," چن":303," ڈا":359," ڈي":297," چھ":653," چک":241,"کٹر":175,"کيے":174,"کي۔":282,"کلا":210,"کلو":610,"کلي":168,"کيا":2343,"کيو":230,"کيم":299,"کين":186,"کيل":348,"کمي":186,"کمل":193,"کنا":202,"کوئ":495,"کور":176,"کوم":779,"کرا":507,"کتے":245,"کسي":1209,"کست":1507,"کزي":242,"کري":262,"کرت":1247,"کرد":421,"کرن":1152,"کرک":265,"کار":1107,"کائ":219,"کئي":281,"کان":309,"کام":558,"کال":425,"کتي":199,"کثر":209,"کتا":937,"کم ":404,"کل ":646,"کن ":715,"کي ":12997,"کو ":5510,"کر ":2045,"کز ":207,"کس ":278,"گور":172,"گري":1479,"گرو":225,"گرد":220,"گرا":170,"گاہ":224,"گئے":444,"گار":222,"گئي":576,"گي ":628,"کہل":354,"کہت":572,"کہا":1480,"کھا":567,"کھت":425,"کھو":307,"کھن":402,"کھي":483,"گر ":1024,"گا ":209,"کے ":18223,"کچھ":310,"کھ ":350,"کہ ":4209,"ا، ":388,"ھا۔":1135,"ھائ":250,"ں۔ ":2401,"ھان":195,"ھار":432,"عہد":221,"ھتے":283,"پان":548,"پار":326,"پاس":169,"پائ":259,"ہ، ":321,"پي ":246,"ئي ":3847,"ات ":5026,"اح ":512,"اج ":434,"ئم ":385,"پرو":236,"پري":221,"ئل ":289,"اب ":1615,"اء ":706,"اؤ ":172,"پاک":1528,"پنج":401,"پنا":177,"ئع ":214,"پور":484,"پني":552,"ئش ":369,"ھي ":3674,"ئر ":279,"بت ":362,"فر ":258,"ان ":9264,"با ":254,"فظ ":915,"ہم ":759,"اً ":534,"ہو ":977,"پنے":725,"اف ":395,"پيش":361,"پيد":1076,"ام ":5824,"ال ":3321,"ہي ":1279,"اق ":313,"اظ ":454,"اع ":255,"ہائ":399,"ہات":210,"ہار":307,"ار ":4602,"اخ ":174,"فت ":347,"اد ":2459,"ہاں":875,"اص ":271,"از ":1002,"اس ":6443,"ہان":212,"ارے":550,"اطا":177,"ھوا":216,"اسک":1125,"ت، ":322,"بي ":1989,"اضي":270,"بو ":188,"اصط":318,"اصل":1371,"ارہ":558,"اسے":795,"اعت":501,"اعد":311,"اعر":317,"ھوٹ":341,"ھيل":511,"اطي":187,"ھنے":355,"اعظ":290,"ھوں":204,"اعل":259,"قع ":1257,"فار":420,"ھيں":343,"فات":329,"فاظ":273,"ادا":654,"اخل":199,"اتھ":922,"ھي۔":577,"احي":174,"اخت":714,"احم":281,"احت":209,"ئي۔":457,"ہا ":1654,"ارا":821,"ادي":1677,"ئيں":363,"ادل":266,"ادب":182,"ادت":200,"بق ":617,"ادر":214,"اتے":523,"ازي":292,"است":1978,"اري":1870,"ارن":318,"ارو":652,"ہت ":499,"ارف":181,"ارس":382,"بل ":520,"ارد":993,"ارت":911,"ارک":342,"اشي":236,"اسم":259,"ادہ":769,"اسل":804,"اشا":172,"اسي":947,"ارٹ":196,"بن ":873,"بع ":355,"ائد":205,"ائر":395,"ائش":451,"ائع":219,"ائن":582,"ائم":404,"ائل":355,"ائي":3099,"ئنس":292,"ابت":325,"ابر":254,"اؤں":202,"ہد ":227,"ابي":488,"ابل":415,"ابق":678,"ابو":358,"ابن":262,"اتح":175,"اتا":3152,"ہر ":2189,"اثر":224,"ؤں ":253,"اتي":1903,"قت ":631,"ائے":1094,"اجا":187,"بر ":849,"في ":604,"عظي":276,"عظم":356,"پڑھ":180,"عري":274,"عرو":255,"عرب":766,"عرا":186,"عدا":424,"عدد":310,"عثم":220,"ظيم":431,"عبد":345,"عات":242,"شہو":678,"شہر":1734,"عال":536,"عام":681,"عاش":251,"عار":177,"صے ":201,"پہن":208,"پہل":895,"غرب":546,"طہ ":206,"عيا":204,"عيس":213,"پھر":309,"پھي":228,"عمل":531,"عمو":341,"عمي":283,"عمر":256,"غان":180,"عني":881,"غاز":188,"علا":1570,"علق":602,"علي":1229,"علو":368,"عما":1154,"علم":738,"آتا":178,"آئي":238,"آبا":1188,"آخر":190,"آزا":306,"ھر ":618,"آن ":225,"ھا ":1233,"غير":796,"آيا":202,"عے ":290,"آپ ":665,"عہ ":760,"جسم":317,"جزي":258,"خت ":294,"جرا":223,"جري":262,"شعب":197,"جزا":198,"جرم":182,"بکہ":367,"ثيت":188,"ذہب":185,"شما":1408,"جبک":363,"اہم":638,"جائ":411,"اہل":181,"جات":4030,"اہو":304,"جاب":370,"جاس":338,"اہي":375,"جار":388,"جان":1341,"جام":298,"رے ":1358,"بہت":604,"رکز":477,"بہا":219,"صبہ":185,"جما":288,"رکا":241,"صحا":176,"رکي":303,"صدر":477,"حال":384,"جنو":753,"ہے۔":9056,"صدي":342,"حاد":180,"حاص":632,"حاظ":206,"جمع":225,"جمو":257,"شيا":452,"خط ":169,"بھي":3076,"بھا":585,"ضي ":277,"صطل":323,"جسے":332,"رکھ":862,"صرف":317,"جسک":274,"زہ ":268,"طب ":280,"تک ":956,"خي ":172,"حرک":215,"حضر":635,"حصي":251,"دت ":251,"حدہ":191,"سٹي":260,"حسا":181,"دا ":1143,"حسن":171,"سٹر":203,"حرا":239,"حري":437,"طح ":229,"تہ ":472,"تھ ":814,"صوص":325,"ہے،":923,"صول":176,"حدي":195,"صور":542,"صوب":1118,"رہي":215,"رہن":216,"جمہ":270,"رہا":394,"جنگ":528,"جيس":335,"رہت":193,"صلا":189,"جود":775,"ضرت":619,"ضرو":182,"خان":852,"خاص":306,"خار":176,"حمد":801,"حقي":267,"تے ":3295,"رہے":389,"صيل":310,"دس ":176,"در ":1119,"دد ":492,"حصہ":359,"دن ":286,"ٹا ":239,"دو ":1561,"ظر ":265,"خصو":323,"ر، ":449,"دي ":2904,"حير":216,"ضلع":1009,"حيا":329,"ختل":505,"حيث":191,"ختي":341,"سے ":11230,"طان":608,"طال":493,"طاب":536,"طبي":334,"دل ":339,"دم ":215,"خلي":574,"سکت":863,"تہا":216,"سکا":323,"سکي":300,"خلا":443,"سکو":402,"دان":840,"دال":423,"تھے":1383,"دائ":580,"دار":1737,"داز":181,"داد":564,"طرح":391,"طرز":173,"طرف":300,"خوا":291,"خود":282,"طري":194,"ظم ":393,"شہ ":199,"سکے":358,"خيا":180,"عت ":511,"تھي":1189,"عد ":1126,"تھا":1925,"رج ":392,"ٹي ":724,"رت ":2032,"رد ":384,"طلب":258,"طلا":420,"عض ":255,"رح ":408,"طور":1195,"ظام":601,"طنت":356,"شکل":258,"را ":761,"دست":238,"رب ":643,"ظاہ":223,"درس":185,"درج":475,"درا":374,"دري":711,"جہ ":949,"درم":359,"درو":190,"دون":230,"ظري":241,"صہ ":469,"دور":724,"دوس":950,"دني":624,"دوں":249,"رف ":993,"ديو":334,"ديم":368,"دين":825,"ديل":228,"ديا":819,"ديت":278,"ديد":212,"ٹر ":1167,"رس ":290,"عي ":320,"دما":182,"جے ":273,"اقو":437,"اقي":177,"اقت":219,"اقا":176,"افي":307,"اقع":1323,"الق":182,"الف":464,"الل":695,"الي":1802,"ان،":219,"امت":248,"اما":469,"الن":229,"الم":986,"الو":429,"امر":725,"الج":351,"الت":351,"الب":611,"الا":1303,"الس":179,"الر":180,"الد":643,"الح":530,"الع":407,"ري ":3579,"جگہ":221,"افر":440,"افت":417,"ٹري":255,"انے":1223,"ايم":221,"انہ":1162,"ايو":177,"ايس":1069,"انگ":1569,"ايش":229,"امہ":269,"ايا":902,"ايت":316,"انک":290,"اير":272,"، ":8315,"بحي":221,"اوہ":305,"رو ":291,"بحر":243,"اقے":283,"ديگ":275,"اني":2788,"انو":1426,"ديک":357,"رق ":406,"باً":193,"اقہ":415,"بان":1448,"بال":507,"اند":1077,"باد":1658,"باز":180,"بار":1042,"انس":905,"امن":202,"انا":720,"انب":309,"امو":288,"انت":736,"بات":454,"امي":1316,"انج":263,"امل":979,"بائ":435,"الے":826,"بتد":219,"اوي":243,"انڈ":193,"انچ":276,"الہ":394,"اون":198,"اول":497,"اوق":178,"اور":10590,"الک":535,"رم ":316,"ذري":244,"اوا":211,"تا ":6076,"حکو":764,"حکم":277,"رحد":298,"ردو":947,"ردي":295,"ردا":370,"رتے":586,"رتا":498,"ايک":5551,"بدا":306,"راچ":302,"ربع":318,"بدي":235,"برا":685,"ربي":855,"ذيل":186,"راہ":513,"برط":276,"برق":294,"بري":212,"رتي":676,"راک":232,"جہا":530,"تر ":480,"ران":1556,"ربا":206,"راع":230,"راف":173,"رام":330,"رال":643,"راب":283,"رائ":562,"راج":355,"رات":605,"راث":218,"رار":318,"راد":611,"راص":190,"راس":245,"ہيں":6226,"بعد":1053,"تح ":170,"ہو۔":237,"جھي":195,"بعض":255,"رآن":223,"بني":578,"بنا":831,"ہوگ":285,"ہوں":722,"بند":385,"ا ":36261,"بلن":294,"ہنچ":177,"بلو":291,"بلي":191,"ہلے":442,"سر ":306,"بلا":185,"ب ":6862,"ء ":3203,"ہوئ":1384,"ہور":1098,"ہوت":2264,"ہوا":926,"ہون":793,"ہلي":355,"ہند":711,"ہمي":171,"ؤ ":175,"زي ":1743,"رطا":394,"ح ":1752,"ھے ":736,"ہلا":565,"خ ":788,"رسٹ":177,"د ":10666,"بوں":222,"بيٹ":246,"ست ":854,"ذ ":232,"بين":440,"بيل":268,"سا ":510,"رست":341,"بيع":188,"ت ":16193,"بيا":321,"بير":253,"رسي":336,"سب ":865,"رجہ":199,"ث ":408,"بول":436,"ج ":1790,"بلک":176,"سم ":677,"دہ ":2099,"تي ":4132,"سل ":210,"اک ":371,"ريہ":436,"تو ":819,"ٹلي":171,"ريک":876,"دھ ":232,"روں":847,"رپ ":187,"ريع":323,"رين":690,"ريل":294,"ريف":299,"ريق":376,"رنے":958,"تم ":196,"ريا":1581,"ريب":696,"ريخ":486,"ريت":171,"ريز":1341,"ريش":173,"رنگ":273,"روف":378,"رون":314,"روم":315,"روع":324,"رور":309,"روز":221,"روس":205,"روا":481,"اپن":1352,"ہزا":285,"ہري":293,"زبا":959,"زار":465,"رند":247,"زاد":421,"ہرا":229,"رمي":582,"رمن":177,"رنا":383,"زائ":318,"رما":229,"اٹل":178,"ہتے":651,"ثر ":284,"؛ ":306,"سط ":176,"رقي":620,"رقب":303,"ہجر":225,"ئے ":2320,"تبد":215,"تان":2396,"تبا":381,"تار":774,"تاب":521,"اچي":318,"دے ":517,"سن ":294,"ہے ":7219,"اں ":1697,"سو ":217,"تحر":360,"شت ":170,"تحا":210,"تحص":253,"سي ":3401,"تدا":329,"اہ ":1042,"تري":474,"ترا":469,"جا ":352,"تصا":242,"جب ":430,"تصو":215,"ترک":411,"اڑي":213,"ستہ":193,"تظا":196,"سري":335,"تعا":188,"سرح":298,"سرا":421,"تعم":1291,"تعل":965,"تعد":362,"دگي":389,"جد ":384,"شن ":295,"زما":353,"سام":409,"سال":748,"سان":757,"زند":314,"جس ":1740,"سائ":617,"زمي":343,"سات":868,"ساب":328,"ستا":2494,"تقا":197,"سجد":245,"تقر":347,"تقس":240,"ستع":1050,"زيا":694,"ستي":192,"ستو":208,"زيد":178,"اے ":199,"زير":703,"تمل":297,"ا۔ ":2384,"صر ":373,"تلف":484,"تما":488,"اۓ ":304,"سلا":945,"تين":302,"سمج":250,"سلي":236,"سمب":188,"سلم":718,"سما":225,"تيس":201,"تيا":780,"سلط":553,"سلس":275,"توا":248,"شي ":269,"سطح":252,"تيں":193,"پر ":4411,"اکي":196,"اکا":303,"اکس":1424,"سرے":373,"توں":404,"صد ":229,"ٹے ":294,"اگر":397,"جن ":581,"بڑا":364,"رک ":436,"بہ ":1879,"اکھ":210,"رہ ":1976,"جي ":406,"شرق":569,"شرو":345,"شري":335,"صل ":1226,"جو ":2871,"بڑي":256,"حت ":262,"ئے۔":600,"بڑے":246,"حد ":400,"ھے۔":835,"سوي":178,"شتر":182,"سوا":232,"سور":248,"شاع":346,"شام":808,"سمن":228,"شائ":191,"سند":323,"شاخ":186,"سمي":191,"ثلا":193,"شخص":263,"ثما":224,"ذکر":233,"اہر":591,"اہد":216,"سين":345,"سيم":308,"شاہ":679,"شتم":303,"سيد":218,"بے ":441,"سيا":755,"ڑا ":500,"ٹھ":533,"پت":249,"پا":3394,"پس":366,"پش":179,"پر":5467,"ٹے":304,"گ ":1702,"ٹک":243,"پڑ":366,"پو":978,"پن":2069,"پي":2662,"پل":260,"ٹي":1294,"ٹو":369,"ٹن":221,"ٹل":297,"ٹر":1769,"ٹا":643,"ک ":9401,"لے":2164,"يں،":396,"مگ":395,"مک":804,"نڈ":840,"وي":2835,"ي،":686,"نچ":605,"وو":294,"يب":1474,"يا":18357,"مہ":1477,"يئ":237,"يع":1465,"يز":2169,"يس":3006,"نگ":3438,"يش":1424,"يص":226,"يخ":630,"يد":2958,"ير":4679,"يت":2515,"يث":342,"يج":682,"نک":1176,"يح":396,"ين":5944,"يو":3744,"وچ":363,"نھ":192,"يق":966,"يم":3458,"نہ":3293,"يل":3575,"يف":992,"وپ":411,"وٹ":898,"وڑ":349,"نے":8036,"وڈ":316,"يٹ":1722,"وک":763,"پ ":1225,"يٰ":198,"وگ":857,"وہ":2577,"يچ":216,"يڈ":589,"وں":7039,"يپ":229,"و۔":276,"يک":8185,"يگ":581,"يہ":6841,"يں":24637,"ي۔":1652,"يۓ":606,"يے":1374,"فع":234,"فض":206,"فظ":975,"فر":2018,"فس":304,"فت":956,"فا":1934,"يہا":454,"قع":1462,"قط":251,"قص":525,"قس":674,"قر":1456,"قد":958,"قت":918,"في":1664,"قب":1358,"فو":716,"قا":2876,"فن":259,"فل":626,"فق":170,"فٹ":222,"قي":2110,"ل،":228,"قل":641,"قو":1321,"لق":994,"لف":1951,"لط":721,"يں۔":3302,"لغ":238,"لع":1546,"لد":859,"لج":430,"لح":953,"لز":212,"لس":945,"لر":265,"لئ":340,"لا":9180,"لت":997,"لب":1083,"مع":2282,"مغ":639,"مص":529,"مض":257,"مط":1001,"مف":327,"مق":1607,"مل":3799,"مت":2835,"لو":3381,"مج":828,"لي":9899,"ن،":378,"مث":441,"لم":3135,"لل":728,"مب":937,"لن":899,"ما":9656,"مز":517,"مر":3546,"مش":2018,"مس":1772,"مخ":947,"مح":1397,"مذ":278,"مد":1699,"نظ":1248,"نع":313,"نل":169,"قہ":970,"نم":856,"نق":463,"نف":515,"ے، ":1325,"نج":1093,"مي":23019,"نت":1838,"مو":3519,"نب":733,"نا":7139,"من":2588,"فہ":638,"مم":631,"نص":409,"نش":418,"نس":2278,"نز":337,"نر":275,"ند":4576,"قے":375,"مپ":203,"وئ":2114,"وا":9079,"نن":295,"نو":3979,"ني":8247,"و،":187,"ٹ ":1461,"لڑ":176,"وغ":354,"نٹ":588,"وع":906,"وق":1147,"وف":901,"ون":4062,"ول":2928,"وم":3387,"لہ":2193,"وت":3089,"وب":2645,"ود":2057,"لک":2192,"وح":206,"وج":2206,"لگ":620,"وس":2774,"وز":895,"ور":18253,"وط":241,"وض":250,"وص":445,"وش":613,"يکھ":326,"ڑ ":321,"يکن":476,"يکي":320,"يگر":286,"چ ":481,"يکہ":301,"ڈ ":843,"خو":1180,"دت":297,"دا":6455,"دب":338,"خي":646,"خل":1333,"خم":176,"تہ":894,"تھ":5631,"خط":526,"خر":474,"خد":295,"خص":603,"دو":4578,"ر،":467,"دي":7480,"دف":241,"دل":705,"دم":634,"ذا":327,"دن":1041,"تے":3362,"دع":168,"دد":552,"در":3958,"دش":266,"دس":695,"جي":1296,"جو":4658,"حت":458,"جن":2503,"حا":2227,"حب":298,"جل":349,"بہ":2825,"جم":1355,"بھ":4084,"ا۔":3031,"اۓ":335,"اے":213,"جس":2866,"جز":533,"جر":1045,"جد":723,"بک":601,"خت":1742,"حي":1318,"تک":1171,"حم":1392,"خا":1967,"خب":324,"حو":294,"حق":534,"حل":497,"حض":792,"حص":974,"بے":458,"حر":1330,"حس":621,"حد":976,"تف":294,"تم":1316,"تل":864,"تق":1058,"تو":2257,"بچ":213,"ثا":431,"تن":759,"تج":398,"تح":1528,"تر":2642,"تخ":631,"تد":422,"اڑ":396,"تش":356,"تص":699,"تس":246,"تظ":210,"تع":3085,"اں":1731,"ثل":246,"جا":8260,"ثم":243,"اہ":3738,"جب":952,"ثي":412,"تي":6367,"اک":3503,"ثر":502,"اگ":766,"بڑ":994,"ئے":3028,"ؤں":259,"بغ":203,"بع":1847,"بن":3272,"بم":183,"بل":2052,"بق":773,"بد":925,"اً":548,"بج":198,"بح":566,"بت":774,"اي":9647,"او":12882,"بط":281,"بص":181,"بز":199,"بس":224,"اُ":281,"بر":3415,"اپ":1892,"اٹ":526,"تا":10999,"اچ":510,"تب":1015,"بو":1546,"ت،":328,"بي":4832,"ئد":211,"ئر":536,"ئش":454,"ا،":402,"اء":804,"اؤ":588,"ئل":407,"ائ":7576,"ئم":430,"ئع":221,"از":2184,"ار":13604,"اد":7175,"اض":766,"اص":2408,"اش":1157,"اس":13319,"ات":12391,"اب":5157,"ئن":668,"اخ":1510,"اح":1946,"اج":1405,"اث":517,"ئي":5602,"اف":2468,"اق":3776,"ام":10852,"با":7594,"ان":23472,"ال":15347,"اع":2513,"اغ":318,"اط":844,"اظ":619,"آپ":794,"آئ":413,"آب":1377,"آت":374,"آج":214,"آخ":195,"آر":259,"آس":262,"آز":333,"آف":182,"آل":275,"آم":177,"آن":518,"آي":281,"عے":301,"ٰ ":195,"عہ":1012,"طہ":234,"غي":910,"غل":246,"عي":1223,"غر":737,"صے":202,"عق":239,"عل":4649,"صہ":487,"عم":2601,"غا":645,"عن":1246,"عو":588,"عث":370,"ظي":492,"عت":818,"عد":2145,"عز":175,"عر":1942,"عظ":634,"عض":358,"عا":2408,"عب":841,"ظم":515,"شہ":2846,"ظا":851,"طن":541,"سہ":287,"طل":743,"سے":11317,"ظر":549,"شک":686,"طي":706,"طو":1493,"ضم":182,"زہ":344,"ضل":1190,"رے":1402,"طر":1375,"ضي":496,"سک":2597,"طح":262,"طا":2021,"طب":814,"ضو":288,"سپ":375,"صل":1848,"صف":401,"صط":357,"سٹ":824,"ضر":887,"صو":2504,"رہ":3575,"صن":434,"ضا":582,"صي":766,"دے":538,"شع":464,"رک":3328,"صح":404,"صد":1147,"صر":962,"رگ":411,"شم":1789,"ذہ":258,"صا":794,"شن":774,"صب":345,"شو":358,"شي":1319,"سع":252,"سط":727,"دگ":457,"سف":448,"دھ":774,"رپ":455,"رٹ":425,"رڈ":213,"سي":6156,"شت":955,"رچ":305,"سو":1823,"شا":3056,"سن":1275,"دہ":2389,"سم":1996,"سل":3485,"شر":1691,"شد":243,"شخ":304,"ذک":274,"سب":1244,"سا":5309,"زن":603,"ست":5770,"زو":460,"زم":950,"زل":234,"سر":2705,"سج":282,"زي":3808,"دک":188,"رس":1755,"رش":298,"رر":201,"رز":482,"جے":273,"رط":461,"رص":252,"رض":357,"رل":427,"رق":1634,"رف":1286,"رو":5304,"زب":1100,"رن":2342,"زا":1886,"رم":1656,"ري":12753,"زر":534,"ذر":554,"جگ":285,"رآ":320,"جھ":599,"جہ":1619,"رب":2493,"را":9267,"رت":4343,"رج":1190,"ذي":412,"رخ":287,"رح":1014,"حک":1119,"رد":2466,"ف ":3475,"ع ":4219,"ڑي ":543,"غ ":230,"ص ":761,"ض ":697,"ط ":839,"ظ ":1429,"ر ":38086,"ز ":2573,"س ":11232,"ش ":1550,"ِ ":847,"ً ":542,"ي ":57056,"ن ":18794,"و ":15262,"ق ":2735,"م ":14225,"ل ":13265,"ينہ":361,"ينے":248,"يوں":1103,"وہ ":2016,"يقي":265,"يلا":274,"يلي":664,"يما":422,"يلو":184,"ينا":221,"نہي":1033,"يمي":391,"نہو":438,"يٹ ":181,"يني":579,"يقہ":243,"وچس":192,"يور":512,"يوا":288,"يون":715,"ينڈ":257,"وں ":6861,"ہے":17450,"يٰ ":189,"وٹي":197,"يعے":209,"وگ ":226,"يرہ":738,"يشي":298,"يشن":306,"يسي":670,"نگي":216,"نگل":243,"يسو":203,"يسر":205,"ے،":1342,"نگر":1405,"يزي":1326,"نگا":269,"يسا":524,"يرو":314,"يري":407,"يعن":649,"يسے":586,"۔ا":238,"يثي":187,"يا۔":1172,"نکا":269,"ے۔":10861,"يتي":187,"ياں":353,"يرا":565,"نکہ":250,"يدا":1270,"نے ":7909,"يال":283,"يان":856,"يبا":352,"يام":192,"ياس":748,"يار":881,"ياد":1222,"ياض":232,"ياء":241,"يات":2312,"ياب":173,"يائ":508,"کچ":345,"کٹ":398,"کي":17718,"ي۔ ":1247,"کس":3186,"کش":375,"کر":6688,"کز":505,"کث":328,"کت":1905,"کو":8220,"کن":1311,"کم":1336,"کل":1933,"کئ":359,"کب":357,"کا":13105,"يۓ ":585,"يے ":1282,"گہ":320,"گھ":468,"گل":520,"گن":309,"گو":1092,"گي":2325,"گز":223,"گر":3536,"گئ":1042,"گا":1385,"کے":18417,"کھ":2829,"کہ":6908,"ں،":524,"گے":188,"يہ ":6011,"يڈي":227,"ھے":1744,"ہز":291,"ہر":3373,"ہج":298,"ہت":1501,"ہد":644,"ہا":4675,"ہب":255,"ہي":8193,"ہل":1738,"ہم":1207,"ہن":1510,"ہو":9694,"ں۔":3376,"ھم":206,"ھل":258,"ھي":5556,"ھو":1393,"ھن":692,"ہ،":328,"ھر":965,"يں ":20810,"ھا":3850,"ھت":572,"ں ":29650,"ڈر":227,"چي":975,"چن":411,"چو":627,"وہا":172,"ڈا":533,"چک":371,"چہ":230,"چھ":1116,"ڈو":318,"ڈي":856,"پھ":684,"پہ":1407,"چس":237,"چا":849,"چت":269,"چل":282,"ڑا":619,"ۃ ":184,"ۂ ":441,"ڑے ":367,"يٹر":982,"ڑي":670,"يک ":5968,"ھ ":2275,"چے":173,"ہ ":29676,"وگو":199,"ڑک":206,"ڑھ":467,"ڑے":384,"ے ":59880,"ۓ ":1150,"۔ ":15851,"و۔ ":200,"وز ":174,"ور ":14043,"ود ":1161,"ڈي ":274,"لگ ":206,"وس ":423,"چين":228,"نما":532,"وع ":503,"نيا":1482,"نوي":380,"نون":235,"نور":347,"نوب":664,"نوا":373,"نٹ ":234,"وف ":378,"نيہ":422,"نيو":458,"نوں":1111,"وم ":918,"لہ ":1961,"ون ":1017,"چند":174,"ول ":1088,"نڈ ":285,"وي ":1068,"ي، ":669,"نچ ":177,"مغر":519,"معل":267,"معن":336,"معر":258,"مشہ":684,"معا":596,"چست":201,"مقا":854,"مقد":219,"چان":177,"ملت":253,"ملا":357,"چتر":233,"قے ":368,"منا":208,"نائ":404,"مند":339,"نات":285,"منت":213,"نار":304,"مما":299,"ملي":227,"موا":174,"ملک":619,"موج":660,"مور":225,"موس":304,"موع":240,"نام":2044,"نان":513,"ناي":217,"نتق":217,"نتظ":204,"نتخ":209,"مون":289,"موم":337,"مول":250,"ميل":269,"ميد":233,"مير":641,"ميا":812,"ميت":203,"نتي":206,"نجا":562,"مين":762,"ميٹ":952,"موں":292,"ندا":677,"ميں":16302,"ندو":448,"ندر":713,"ندي":569,"چار":237,"نسا":448,"چي ":376,"وا ":736,"ندگ":273,"ندہ":249,"نسي":397,"نسل":289,"ندھ":311,"وب ":577,"وت ":377,"نظا":416,"نظر":493,"وج ":244,"نظي":172,"لک ":878,"ونا":319,"ومي":882,"ونس":207,"وما":454,"ولي":616,"ولو":168,"ومت":782,"يع ":214,"ولا":396,"وقت":472,"وفا":282,"يش ":423,"يس ":618,"نگ ":881,"ويں":364,"يق ":261,"يف ":611,"مکم":188,"ونے":813,"نڈي":216,"چہ ":203,"ونک":263,"چھ ":368,"وني":567,"وٹ ":170,"ونو":241,"وڈ ":203,"يو ":296,"نہ ":1535,"يم ":2131,"ين ":3424,"مگر":341,"يل ":1806,"لے ":2120,"وئے":873,"واں":205,"وتي":759,"وتا":1184,"وبہ":880,"وجي":169,"وجو":858,"وا۔":228,"وار":699,"واز":279,"واد":234,"واج":227,"وئي":1076,"واب":205,"وائ":356,"وبي":420,"واي":171,"واق":1340,"وال":2546,"وان":598,"وبا":263,"وام":369,"وري":875,"مہ ":911,"وست":275,"لگا":240,"وزي":317,"يا ":8493,"وسر":713,"وسط":295,"ورپ":286,"ودہ":176,"وسي":366,"يب ":717,"ورہ":195,"لکي":197,"وتے":500,"ودي":279,"ورا":750,"وجہ":615,"ورس":204,"ورت":506,"لکہ":196,"ورن":218,"لکھ":453,"وغي":292,"يد ":1164,"ير ":2092,"يز ":500,"يت ":1838,"يج ":176,"يح ":219,"يخ ":423,"لد ":289,"قصب":216,"لت ":358,"لا ":1251,"قسم":285,"لب ":395,"قسي":239,"�":423,"لق ":599,"لف ":570,"چھو":396,"قوں":260,"ما ":498,"لم ":1252,"لع ":962,"قيق":283,"قيا":359,"قوم":305,"قوا":311,"قل ":209,"فرا":633,"فرو":181,"فري":361,"قي ":950,"ل، ":225,"فيص":180,"قبہ":284,"قدر":190,"قدي":366,"قري":696,"قرآ":222,"قرا":218,"قال":197,"قائ":507,"قاب":316,"قات":245,"فلم":218,"فوج":255,"قبو":176,"قبل":223,"قان":205,"قبا":188,"قام":703,"فٹ ":202,"لما":635,"ماع":315,"لمي":331,"مات":656,"مار":1346,"ماد":258,"لند":373,"مائ":379,"لفظ":904,"لفا":303,"نس ":426,"لعہ":239,"ند ":917,"لطا":204,"مي ":1920,"لطن":355,"مطل":234,"ني ":4359,"و، ":185,"مطا":719,"مصن":197,"مصر":194,"مرک":583,"نو ":281,"مذہ":183,"مشر":609,"مسل":679,"مشت":387,"مست":254,"مسج":242,"مسا":197,"قہ ":928,"مري":646,"مجھ":254,"مرا":743,"مرب":331,"مرت":186,"مدي":169,"ليے":1014,"ليۓ":470,"مدد":185,"ليک":538,"ليہ":571,"مخت":598,"لوگ":423,"محم":603,"لوں":448,"لوچ":226,"لين":425,"مجم":256,"لنے":191,"ليت":222,"متي":175,"ليا":836,"ماہ":260,"ليم":656,"مثل":227,"لوي":317,"لوم":894,"للہ":672,"متح":211,"متع":399,"مال":2414,"مام":560,"مان":1742,"مبا":175,"ماي":231,"مبر":417,"مر ":315,"مد ":873,"لو ":198,"ے۔ ":8070,"مت ":1234,"لي ":3595,"ن، ":362,"لسل":386,"نب ":260,"نا ":1656,"من ":398,"فہ ":313,"نت ":572,"لدي":343,"لحک":303,"مل ":1925,"لتي":176,"لاک":279,"لئے":321,"لاہ":228,"لتا":182,"لحا":247,"لاح":555,"لاد":170,"لاز":192,"لائ":397,"لات":751,"لاق":1241,"لاف":367,"مع ":244,"لاو":376,"لام":1294,"لان":427,"لبا":312},"n_words":[1602570,1999510,1324903],"name":"ur"}
\ No newline at end of file
text/langdetect/profiles/vi 0 → 100644
View file @ b309ea1b
{"freq":{"D":18934,"E":10094,"F":9985,"G":23207,"A":42579,"B":48257,"C":72224,"L":45665,"M":47574,"N":70917,"O":10000,"H":57302,"I":15743,"J":5371,"K":22108,"U":5400,"T":104616,"W":8071,"V":30021,"Q":14744,"P":61692,"S":43824,"R":17604,"Y":3509,"X":6207,"Z":3364,"f":32992,"g":525146,"d":205922,"e":428748,"b":182777,"c":671453,"a":692878,"n":1382200,"o":437498,"l":442210,"m":420259,"j":4762,"k":100510,"h":937660,"i":759263,"w":22119,"v":178461,"u":410719,"t":952446,"s":286409,"r":444790,"q":33677,"p":174320,"z":16996,"y":192811,"x":29082,"²":689,"Î":330,"É":501,"Á":3556,"Â":2373,"Ý":1288,"ß":648,"Ú":1274,"Ô":1751,"í":49339,"ì":32480,"ê":66073,"é":38397,"è":3862,"ç":233,"ä":808,"ã":19808,"â":112923,"á":116051,"à":337783,"ü":3187,"ý":5197,"ú":10002,"ù":30808,"ö":2319,"ô":98885,"õ":1117,"ò":13544,"ó":78081,"ñ":390,"đ":198318,"Đ":41649,"ă":37793,"ā":557,"ĩ":9562,"ī":249,"ō":772,"ũ":5403,"ū":650,"ư":147894,"ơ":25607,"́":204,"ο":236,"ι":146,"λ":139,"α":217,"ς":203,"ρ":170," l":242575,"ь":159," m":173509," n":244497,"я":194," o":12009," h":134731," i":13655," j":644,"ы":142," k":76050," d":93354," e":7007," f":8319," g":49741,"ч":190,"р":638,"с":522," a":22488," b":142456,"т":441,"у":252," c":262807," y":1958," x":17955," z":365," u":1259," t":566783," w":4693," v":156401," q":28586," p":59115," s":94989," r":14869," J":5319," K":22031," H":57162," I":15633," N":70771," O":9935," L":45508," M":47408," B":48077," C":71972," A":42454,"С":156," F":9904," G":23091," D":18825," E":10050,"л":506,"к":551," Z":3238,"й":211," Y":3492,"и":885," X":6141,"о":889,"н":659,"м":235,"г":168," S":43565,"в":508," R":17493," Q":14713,"б":149,"а":1192," P":61533," W":8016," V":29925," U":5377,"е":792,"д":263," T":104253," á":1499," â":3662," í":541," ô":2220," ý":503," ă":627," Đ":41607," đ":198156," Â":2373," Á":3556," É":500," Î":330," Ô":1748," Ú":1274," Ý":1277," ư":1144,"ي":271,"ل":264,"م":187,"ن":142,"ا":398,"ر":178,"A ":2159,"F ":494,"Da":2569,"Cu":1591,"Cy":963,"Cl":1245,"Co":10944,"Cr":1746,"Ce":2576,"Ch":19039,"Ci":1005,"G ":637,"Ec":908,"Ed":361,"Ea":530,"Du":1267,"Dy":152,"Do":2470,"Dr":1247,"De":2217,"Di":2894,"Bà":792,"Bá":858,"Fe":902,"H ":455,"Fa":1831,"Eu":2126,"Ex":464,"Er":617,"Et":367,"Es":894,"En":771,"Em":460,"Ep":314,"Ei":335,"El":872,"Cá":2732,"Ge":2583,"Câ":290,"Cà":157,"Ga":3052,"I ":2174,"Fu":749,"Fr":2327,"Bí":387,"Bì":1773,"Fo":1217,"Bé":191,"Fl":1104,"Fi":1024,"B ":642," С":156,"C ":1227,"Av":428,"Au":2997,"Ar":5387,"Aq":1658,"At":1067,"As":1434,"D ":745,"Ba":13610,"Az":1190,"Ay":139,"Ae":265,"Af":962,"Ag":750,"Ah":192,"Ab":577,"Ac":1193,"Ad":611,"Am":2029,"An":10483,"Ap":626,"Ai":1117,"Ak":164,"Al":6955,"By":154,"Bu":3220,"Br":4012,"Ca":14082,"E ":3496,"Bh":176,"Bi":2488,"Be":3517,"Bo":4388,"Bl":876,"Gò":247,"Ku":658,"Gö":233,"Ky":391,"Kn":144,"Kl":231,"Kr":781,"Ko":952,"Hã":340,"Hà":3871,"Há":6912,"Le":5532,"Li":5716,"N ":1502,"La":11255,"Lu":1591,"Hó":455,"Hò":671,"Ly":614,"Bư":341,"Hé":321,"Lo":11096,"Hì":160,"Me":5622,"Mi":7578,"Cơ":380,"O ":859,"Ma":14564,"Cư":440,"My":979,"Mu":2726,"Mo":6001,"Nh":15252,"Ni":3602,"Ng":8870,"Ne":5246,"Na":14732,"P ":1136,"Dư":2196,"ưu ":1732,"Ny":327,"Nu":290,"No":7260,"Ok":174,"Ol":595,"Om":201,"On":483,"Oh":203,"Oi":748,"Oc":485,"Od":183,"Oe":270,"Oa":270,"Ob":773,"Gi":6635,"Gh":326,"Gl":496,"Gr":4171,"Go":1400,"Gu":2462,"Gy":286,"Cô":3480,"Có":402,"Cú":325,"J ":219,"Ha":7544,"Dâ":1283,"He":2483,"Hi":2709,"Ho":13976,"Hu":4398,"Hy":1927,"Dô":340,"K ":324,"Ib":265,"Id":176,"Ic":220,"Im":190,"In":3623,"Il":428,"Is":1691,"It":2092,"Ir":1003,"Ja":1797,"L ":642,"Ji":230,"Je":710,"Jo":1104,"Ju":1037,"Ka":2594,"M ":626,"Kh":4970,"ưng":2590,"Ki":2990,"Ke":1180,"Ut":638,"Ur":404,"Um":166,"Un":919,"Uk":408,"Ul":140,"Ug":456,"W ":203,"Ty":201,"Tw":155,"Tu":2972,"Tr":21381,"To":2690,"Th":42787,"Ti":3875,"Te":2952,"Ta":3822,"V ":758,"Sw":579,"Sy":613,"St":3687,"Su":1921,"Wo":921,"Wi":1647,"Wh":297,"Sé":358,"Sè":329,"Wa":2024,"Sâ":534,"Sá":354,"We":2017,"Sà":247,"Y ":322,"Lư":806,"Vo":1915,"Vu":318,"Vi":16219,"Ré":208,"X ":401,"Va":2214,"Ve":2267,"Uy":394,"Lă":215,"Mã":1030,"Má":214,"Lý":664,"Lü":151,"Mé":245,"Pt":637,"Pu":1475,"Pr":3920,"Ps":557,"S ":1842,"Py":3299,"Pe":2603,"Là":800,"Lã":279,"Pf":1720,"Lâ":833,"Pa":7810,"Lé":142,"Pl":1384,"Po":3931,"Lê":927,"Pi":2275,"Ph":31098,"Os":655,"Ot":301,"Ou":271,"Ov":238," ا":171,"Op":394,"Or":2938,"R ":429,"Kô":237,"Se":3444,"Sc":3122,"Si":2745,"Nă":720,"Sh":1345,"Sm":208,"Sl":522,"Sk":307,"Sr":367,"Sp":2000,"So":3317,"Ru":1170,"Nô":330,"Ry":155,"Nó":11015,"U ":337,"Hư":909,"Sa":11442,"Re":2085,"Ri":2194,"Rh":4441,"Ro":3835,"Qu":14208,"Mô":839,"T ":649,"Mù":252,"Ra":1904,"Mü":183,"Sơ":2030,"Sư":226,"Yê":502,"Xã":2079,"Wü":541,"Xô":549,"ưa ":1620,"Xí":179,"Vĩ":456,"b ":1444,"a ":226759,"Tư":1027,"Vũ":589,"Tù":160,"Tú":283,"Tô":962,"Xy":153,"Nư":140,"Ye":349,"Ya":435,"Yp":239,"Yo":874,"Sĩ":507,"Yv":187,"Yu":292,"Mư":225,"Só":240,"Sô":413,"Tâ":9624,"Tà":542,"Xe":229,"Tá":302,"Sü":308,"Xa":216,"Tê":676,"Xi":420,"Tò":164,"Xu":1093,"Tí":259,"Vù":202,"Vă":1172,"Za":1272,"Và":236,"Ze":739,"Zh":185,"Zi":458,"Vâ":484,"Tĩ":188,"Zu":199,"Võ":191,"i ":212782,"bó":2113,"cà":270,"gd":295,"cá":22579,"ge":11280,"câ":2231,"bú":210,"ga":12467,"bé":224,"fl":1616,"bã":190,"fg":215,"ff":1242,"fi":2497,"fs":160,"fr":3324,"fu":1164,"ft":684,"fo":4267,"bê":1228,"bí":976,"bì":10910,"j ":155,"cù":1871,"cú":386,"gy":681,"có":47444,"gw":161,"cô":5046,"dâ":28874,"dã":502,"dà":2537,"he":41577,"hb":191,"ha":43156,"gn":5754,"gm":577,"gl":1738,"gk":293,"gi":33763,"bă":263,"gh":11779,"gg":570,"cò":3292,"gu":10662,"gt":510,"gs":1016,"gr":2654,"go":8645,"dt":805,"du":4489,"dw":715,"dy":507,"g ":364697,"ea":15752,"eb":3649,"ec":8564,"ed":11541,"de":24490,"dd":556,"dg":298,"df":167,"di":32181,"dh":710,"dk":145,"dm":293,"dl":1043,"do":14691,"dn":264,"ds":1755,"dr":3533,"ew":3323,"ex":3581,"eu":6762,"ev":2827,"ey":3123,"ez":1216,"fa":5205,"h ":178273,"bà":2398,"bá":2351,"fe":2871,"eh":679,"eg":4460,"ef":1217,"ee":4546,"el":24442,"ek":799,"ej":311,"ei":13045,"ep":4148,"eo":14079,"en":49087,"em":10013,"et":12592,"es":40569,"er":51401,"eq":167,"ca":30360,"Xư":246,"e ":134279,"bw":303,"by":1138,"bs":628,"br":3660,"bu":6071,"bt":170,"bn":144,"bo":4357,"bl":1961,"bf":332,"bh":146,"bi":46026,"bb":920,"be":11159,"db":293,"da":38163,"f ":9188,"cy":1022,"cu":9388,"ct":7017,"cs":417,"cq":226,"cr":3098,"co":14606,"cm":248,"cn":200,"ck":4238,"cl":1934,"ci":14195,"ch":129179,"ce":13915,"cc":1731,"Vư":1101,"c ":282171,"az":1913,"ay":20261,"ba":27162,"d ":28581,"at":21123,"as":21308,"ar":46226,"aq":534,"ax":1123,"aw":1934,"av":3839,"au":17184,"ak":3208,"al":35399,"ai":30021,"aj":1274,"ao":21790,"ap":5292,"am":43172,"an":108096,"ac":18572,"ad":10374,"aa":985,"ab":4752,"ag":8446,"ah":2616,"ae":34413,"af":1148,"nu":5357,"nt":26825,"ns":10879,"nr":434,"nq":250,"np":246,"no":9747,"hĩ":3597,"nn":7993,"q ":277,"nz":1727,"dư":2566,"ny":2595,"nx":314,"nw":217,"nv":655,"oe":1614,"of":8008,"oc":9998,"od":5406,"oa":17234,"ob":3593,"ké":466,"om":14342,"kê":1778,"on":100425,"ok":1733,"kè":139,"ol":16267,"oi":9431,"oj":178,"og":4447,"oh":1218,"ot":8950,"m²":659,"hō":191,"os":13276,"ov":4515,"ou":16281,"kì":215,"op":11878,"oo":2896,"or":34485,"oq":166,"gũ":395,"kí":1225,"r ":23753,"ox":666,"ow":4522,"oz":1526,"oy":925,"là":155485,"lá":810,"pe":13642,"pf":220,"lâ":707,"lã":1014,"pa":8707,"ký":795,"lè":430,"pl":2303,"lé":393,"lê":819,"po":6064,"ph":59995,"pi":7555,"lo":48870,"ln":332,"hê":913,"lm":1499,"hé":1262,"hè":446,"ll":28312,"ls":5922,"hí":22956,"lp":3661,"hì":4519,"hó":4714,"lw":160,"hò":5943,"lv":1420,"lu":8343,"lt":3135,"bư":9431,"lz":2455,"hö":169,"ly":7272,"hô":9522,"hú":4659,"hù":1344,"o ":85116,"iß":177,"ià":688,"hü":788,"ma":19960,"mb":6117,"mg":163,"hă":499,"me":15863,"iá":6621,"cơ":2439,"iè":809,"ml":141,"mi":19185,"mn":579,"iê":19338,"mm":3914,"ié":147,"mp":6181,"mo":8059,"mt":201,"ms":1171,"mu":3841,"iô":221,"ió":194,"cư":776,"my":849,"p ":57766,"iú":305,"na":36440,"nb":2672,"nc":9194,"nd":29108,"ne":33625,"nf":985,"ng":422545,"nh":179739,"ni":21672,"nj":602,"nk":2141,"nl":3093,"nm":685,"ju":396,"jo":698,"ki":21387,"kh":39807,"gã":188,"gâ":871,"ke":3413,"gá":300,"gà":10665,"ka":4069,"m ":167316,"gó":565,"gô":2554,"ky":750,"ks":1201,"kt":384,"ku":945,"ko":1602,"cũ":2937,"kr":861,"kk":293,"kl":1148,"km":4687,"kn":974,"li":29575,"lh":510,"lk":1201,"le":28117,"há":50648,"hà":29720,"ld":3791,"hã":1199,"lg":997,"hâ":38191,"lf":811,"la":39723,"lc":719,"lb":2760,"n ":440934,"hr":3391,"hs":2273,"dò":649,"hw":1075,"ht":2057,"hu":96505,"hk":147,"hh":235,"că":337,"hi":59002,"hn":1134,"ho":33760,"hl":2514,"hm":909,"dé":1520,"id":34385,"ic":24617,"ib":3478,"ia":42159,"ih":435,"ig":7165,"if":3529,"ie":18418,"hy":2981,"dù":2108,"k ":5941,"iq":1214,"ir":10741,"is":30398,"it":19216,"iu":2880,"iv":3060,"iw":152,"eó":2057,"ix":1054,"ii":6395,"ij":559,"ik":1883,"il":38718,"im":11936,"in":70002,"io":10270,"ip":6214,"je":426,"ji":826,"iz":1625,"iy":348,"l ":17786,"ja":1818,"nơ":1994,"să":488,"xi":2236,"tê":7401,"xo":824,"té":201,"tì":8961,"xp":151,"tí":18614,"tò":332,"xt":572,"xu":3759,"mư":601,"sô":2011,"ww":348,"só":466,"z ":4461,"xc":234,"xa":2141,"tâ":11580,"tá":3122,"xe":1418,"tà":3376,"wh":1250,"ră":636,"wi":4079,"sè":470,"wl":199,"sé":203,"wn":1808,"sê":269,"wo":1048,"ws":516,"wt":183,"rò":801,"rõ":266,"rô":669,"lư":3756,"rö":667,"rù":551,"y ":123996,"rú":838,"rü":313,"wa":4838,"sâ":1032,"sá":4087,"we":3258,"rè":166,"ré":3552,"vi":14749,"râ":232,"rã":310,"vu":13359,"vr":721,"rì":2865,"rí":1219,"rê":17007,"vo":1414,"uz":955,"uy":40068,"ux":1932,"uw":188,"uv":1489,"ve":8349,"rá":1135,"rà":746,"va":5946,"x ":5085,"ui":7198,"uj":271,"uk":987,"ul":11719,"ue":8283,"uf":658,"ug":2145,"uh":313,"mũ":152,"ur":22852,"us":22737,"ut":11022,"um":8525,"un":37448,"uo":379,"up":2448,"ty":3384,"tz":1632,"tu":10835,"tt":6267,"tw":506,"tv":273,"ub":3534,"ua":12317,"ud":3186,"uc":4195,"w ":3929,"to":19941,"tn":373,"tm":750,"tl":2439,"ts":3488,"tr":168490,"lũ":299,"tp":612,"tg":165,"tf":340,"te":34125,"ti":45992,"th":244395,"v ":848,"tb":456,"tc":539,"ta":22518,"su":6738,"sv":185,"ss":11481,"st":25304,"sy":900,"sw":1422,"sl":2460,"sk":1966,"sn":3570,"sm":2007,"sp":6570,"so":7204,"sr":482,"sq":267,"oà":40273,"sd":636,"oß":224,"sc":6190,"sf":434,"se":16078,"oá":2469,"nă":29159,"sh":6976,"sg":779,"oã":161,"si":19668,"hư":18279,"rz":821,"u ":92839,"nú":1257,"sa":12158,"sb":1450,"rr":9518,"rs":7765,"rt":11056,"ru":33603,"rv":1083,"rw":648,"nó":3472,"nô":498,"ry":4815,"rq":206,"rp":2369,"lĩ":607,"ro":79309,"nê":766,"rn":10149,"né":3611,"rm":6127,"rl":2540,"nç":154,"rk":3126,"hơ":3447,"ri":45411,"rh":1015,"rg":11132,"nâ":296,"rf":2041,"re":31859,"rd":9664,"nà":32104,"า":167,"rc":4893,"rb":3024,"ra":48559,"mù":496,"t ":240212,"gư":23033,"mó":270,"mô":1896,"qu":33189,"ร":145,"mé":23563,"mì":570,"má":2261,"mã":976,"lý":2656,"mà":2647,"s ":83922,"lú":457,"lô":11642,"px":1137,"py":386,"pt":4331,"pu":3257,"lò":168,"pp":2831,"lí":1363,"pr":2803,"ps":2406,"hū":297,"vư":1017,"zè":171,"vũ":680,"tư":4765,"sơ":283,"yê":5321,"sư":822,"xá":866,"xâ":942,"xã":6617,"rư":7067,"xé":140,"vĩ":1312,"xí":212,"vă":2376,"vù":22603,"zz":263,"vâ":231,"zh":389,"zi":1581,"uý":467,"zb":261,"và":46943,"ze":2177,"za":3062,"yz":169,"vò":489,"võ":378,"vô":1031,"zu":1605,"zo":1512,"zn":191,"ví":191,"vì":1173,"zl":195,"yg":495,"yh":272,"tă":382,"ye":2354,"uá":1249,"uâ":5412,"yf":154,"yc":1911,"yd":753,"ya":3754,"yb":311,"tú":167,"tù":418,"nư":35853,"tô":1034,"xy":294,"yx":252,"uô":12078,"yu":633,"yt":872,"ys":3871,"yr":5371,"yp":2222,"sĩ":1785,"yo":1215,"yn":1357,"uê":505,"ym":1622,"ué":319,"yl":3067,"yi":713,"xư":530,"yū":142,"² ":668,"Á ":1673,"Áv":245,"Áo":1420,"Âu":2129,"Âm":150,"Îl":330,"àn":34510,"ào":9571,"àm":2558,"ài":40656,"ã ":15139,"ày":41288,"àu":3190,"ám":1101,"án":28484,"áo":4300,"áp":27542,"ái":6121,"ác":31049,"áy":2255,"áu":552,"át":6111,"âm":6839,"ân":71359,"âu":6947,"ât":496,"ây":27219,"ãn":2862,"ão":485,"ãi":672,"ãy":559,"à ":205928,"á ":8250,"ße":294,"Úc":1243,"Ý ":1285,"Ôn":1610,"アアア":304,"ôi":2574,"ôm":11781,"ôn":48478,"óa":2709,"õ ":900,"ói":993,"óc":731,"óp":293,"ón":6670,"óm":1531,"ô ":34032,"òa":5612,"òm":318,"òn":6337,"ó ":64834,"ña":207,"ò ":1069,"ín":13049,"ít":636,"ìn":20626,"ìm":8528,"íc":17864,"ía":12239,"í ":5056,"ên":48870,"êm":9168,"êu":3630,"éz":154,"ì ":3075,"él":169,"éo":764,"ép":2326,"ém":434,"én":3441,"és":341,"ét":23592,"ér":825,"év":213,"éb":181,"éd":152,"éc":499,"ée":3394,"ég":181,"èn":257,"èo":280,"èr":1433,"ès":603,"èv":444,"ê ":4050,"é ":1396,"Đưể":826,"è ":371,"är":168,"ăm":28997,"ăn":8563,"ăk":142,"đưể":28774,"ān":253,"ý ":5155,"ể":1508247,"ün":249,"ür":1564,"üt":177,"üc":207,"üd":322,"ùn":27807,"ùi":235,"ùa":1067,"úp":776,"ún":1686,"úy":219,"út":637,"úa":606,"ùy":248,"úi":1359,"úc":3127,"ù ":1286,"ú ":1439,"ôt":1632,"öt":180,"ör":366,"ös":634,"ön":312,"öl":155,"đĩ":597,"đó":3828,"đô":27703,"đú":182,"đă":220,"Đư":848," ể":80643,"đư":29695,"đơ":1908,"tưể":2647,"Đa":443,"Đo":196,"Đi":1420,"đe":478,"đa":1708,"đo":2470,"đi":17430,"Đ ":295,"Đì":322,"Đà":1638,"Đá":165,"Đâ":3555,"đí":392,"đì":460,"đê":8064,"đã":4348,"Đă":188,"đá":3730,"đâ":1604,"đà":1035,"Đô":12692,"đu":489,"Cể":8674,"Dể":759,"Bể":9876,"Hể":9168,"Gể":170,"Lể":3634,"Kể":5925,"ĩ ":4602,"ĩa":3526,"ĩn":1420,"ĩnh":1417,"dể":12219,"ĩa ":3523,"cể":67050,"bể":45726,"mể":131131,"ũ ":2155,"lể":23218,"kể":7585,"iể":166241,"hể":264262,"gể":17545,"Sể":1192,"Tể":7402,"Rể":525,"ō ":339,"Mể":5140,"vưể":475,"Nể":1896,"Xể":142,"Vể":1294,"rể":50434,"sể":54959,"tể":83275,"uể":92128,"nể":21381,"ū ":399,"oể":14719,"ũi":200,"ũn":2955,"vể":53705,"专专 ":169,"xể":2191,"yể":31245,"ơi":3100,"ơm":181,"ơn":18072,"ơ ":4182,"あ":270,"ア":496,"가가 ":224,"ươ":12314,"ư ":8494,"ưa":1622,"ưn":2592,"ưu":1733,"Để":19679,"để":91689,"Đan":304,"đa ":614,"ơm ":179,"ơn ":5934,"đai":310,"đan":664,"ơi ":3096,"đi ":743,"ơng":12128,"đen":294,"đo ":419,"đoà":1003,"đua":287,"乙":857,"乘":179,"之":2791,"丹":642,"临":665,"中":142,"並":1114,"丙":309,"丘":935,"丛":252,"专":2269,"且":143,"丈":196,"三":4224,"丁":2034,"万":989,"亞":563,"亂":327,"侏":215,"ểy ":15070,"ểu ":43780,"ểt ":179200,"Đây":3553,"Đào":412,"Đài":765,"Đà ":277,"Đôn":3441,"圓":161,"Đô ":9162,"Đìn":322,"冲":171,"đêm":8016," 丘":335,"đíc":372," 专":413," 三":1027," 丁":795,"đìn":459,"đây":1563,"đá ":2316,"倉":569,"đán":1131,"đã ":4325,"đào":392,"đài":257,"đàn":318,"đún":140," 倉":244,"ưể":121112," 侏":158,"đón":976,"đôi":461,"đôn":8728," 並":342," 临":320," 丹":351," 之":799," 乙":411,"đó ":2805,"đô ":18495," 亂":152,"大":197,"ểa ":61642,"ểc ":245982,"ểch":9163,"ểi ":112695,"ểk ":174,"ển ":203101,"ểm ":59200,"ểp ":25010,"ểng":124564,"ểnh":41635,"ểo ":9528,"Điể":1233,"ああ":156,"điể":16552,"đoể":920,"đăn":218,"đĩa":596,"ς ":202,"đơn":1904," ểc":15788," ển":5390," ểm":264," ểy":799,"アア":391," ể ":57997,"đươ":308,"đưa":612,"ск":150," vư":1017," xư":529," Áo":1420," Áv":245," Á ":1673," Ga":3043," Câ":289," Cá":2724," Ge":2570," Cà":157," I ":489," Bì":1773," Bí":387," Fo":1209," Fu":749," Fr":2319," Fi":1014," Fl":1075," Bé":190," Ha":7534," He":2474," Dâ":1282," Cô":3477," Có":398," Gy":285," Cú":325," J ":162," Go":1392," Gr":4156," Gu":2454," Gh":322," Gi":6622," Gl":488," Id":176," Ic":219," Ib":265," Hy":1924," Dô":340," Hu":4380," Ho":13959," Hi":2699," Ji":227," Je":694," L ":288," Ja":1791," Ir":1002," Is":1688," It":2091," Im":186," In":3565," Il":425," M ":229," Ka":2587," Ke":1169," Ki":2975," Kh":4951," Jo":1090," Ju":1029," N ":147," La":11244," Hà":3868," Há":6905," Le":5519," Hã":339," Li":5628," Kl":231," Kn":141," Ko":946," Kr":777," Gò":247," Ku":656," Gö":233," Ky":391," Ma":14506," O ":139," Cơ":380," Mi":7555," Me":5610," Hì":157," Lo":11086," Hé":321," Bư":341," Ly":614," Hó":455," Hò":670," Lu":1590," Ne":5220,"а ":296," P ":285," Na":14703," Ng":8844," Nh":15231," Ni":3593," Mo":5991," Cư":440," My":978," Mu":2713," A ":801," B ":314," C ":460," Ap":624," Am":2023," An":10467," Ak":163," Al":6944," Ai":1106," Ag":749," Ah":189," Ae":262," Af":957," Ac":1189," Ad":608," Ab":573," Ba":13586," D ":281," Az":1190," Ay":139," Av":424," Au":2992," At":1064," As":1419," Ar":5374," Aq":1657," Be":3504," Bi":2420," Bh":176," Bl":874," Bo":4376," Br":4006," Bu":3207," By":153," E ":175," Ca":14032," Ce":2572," Ci":1003," Ch":19001," Cl":1229," Cr":1732," Co":10896," Cu":1575," Cy":959," F ":217," Da":2548," Di":2876," De":2206," Dr":1245," Do":2436," Dy":152," Du":1262," Ea":529," Ec":908," Ed":358," G ":173," El":867," Ei":335," Et":365," Es":889," Er":614," Ep":314," En":763," Em":454," Ex":456," Eu":2122," Bà":785," Bá":846," Fe":894," Fa":1822," H ":178," Xu":1090," Tò":163," Tí":259," Tê":651," Xi":413," Tà":542," Xe":204," Tá":302," Tâ":9623," Sü":308," Xa":216," Só":240," Sô":411," Mư":225," Wo":905," Sé":358," Sè":329," Wi":1632," Wh":294," Sá":350," We":2007," Sâ":533," Sà":247," Wa":2017,"й ":151," Y ":281," Lư":805," Võ":190," Tĩ":188," Và":232," Ze":737," Vâ":484," Zh":184," Zi":450," Za":1260," Yv":187," Yu":290," Yp":238," Yo":868," Sĩ":506," Ya":432," Ye":349," Nư":140," Tô":962," Xy":153," Tú":282," Tù":160," Xí":179," Vĩ":455," Xô":549," Wü":541," Xã":2079," Vù":202," Vă":1148," Vũ":587," Tư":1025," a ":4962," Yê":501," Sư":226," Sơ":2029," R ":199," Kô":237," Ou":268," Ov":236," Os":655," Ot":299," Or":2938," Op":391," Po":3911," Lê":922," Lé":142," Pl":1371," Pi":2271," Ph":31029," Lã":279," Pf":1720," Lâ":831," Pe":2592," Là":800," Pa":7774," Dư":2196," Ny":327," Nu":290," No":7248," Ol":594," Ok":173," On":479," Om":200," Oh":202," Oi":748," Od":181," Oc":483," Oe":269," Ob":773," Oa":270," Ra":1894," Mü":182," T ":156," Mù":252," Mô":838," Qu":14182," Ro":3827," Re":2068," Ri":2185," Rh":4439," Py":3297," S ":230," Pr":3910," Ps":554," Pt":637," Pu":1471," Mé":244," Lý":663," Lü":151," Má":214," Lă":214," Mã":1026," Sy":607," Sw":578," Su":1915," St":3635," Ta":3810," V ":169," Th":42680," Ti":3850," Te":2931," Tr":21258," To":2625," Nó":11014," Ry":154," Nô":330," Ru":1162," Sa":11420," Hư":907," U ":154," Nă":720," Sh":1334," Si":2727," Sc":3070," Se":3434," So":3300," Sp":1984," Sr":367," Sk":306," Sl":517," Sm":206," Uy":393," Va":2209," X ":200," Ve":2261," Vi":16180," Ré":207," Vo":1912," Vu":317," Tu":2947," Tw":154," Ty":200," Ug":456," Uk":408," Ul":140," Um":165," Un":913," Ur":403," Ut":638," ja":224," l ":250," im":322," in":6639," is":5408," it":773," ka":329," m ":439," kh":38847," ki":18267," gâ":429," ke":373," gá":282," ju":151," cô":5020," có":47410," cú":382," cù":1871," ha":11491," dã":502," dâ":28872," he":621," dà":2524," gi":28288," bă":261," gh":729," gl":236," gr":899," go":250," gu":378," cò":3288," hy":276," dù":2107," că":333," hi":6669," dé":1144," ho":9851," ht":218," hu":16965," dò":646," nh":45517," ni":1927," ng":51853," ne":507," na":15500," cư":775," mu":1888," mo":1972," ké":437," on":1221," kê":1776," oc":375," of":6994," ob":204," dư":2565," nu":602," no":1173," hã":1017," hà":8670," há":923," le":1986," li":4644," la":5104," gó":504," kn":913," km":4476," cũ":2936," ko":246," me":1022," mi":9905," cơ":2426," hù":342,"я ":139," hú":203," ma":3748," lu":1700," hó":2026," hò":4796," ly":382," hô":283," bư":9431," hè":160," lo":35801," hì":2834," ag":160," ab":359," ac":560," ad":220,"Hểu":669," am":614,"Hểp":191," an":7056," ap":254," ai":278,"Hển":822," al":2427," au":545,"Hểi":3718," ar":2712,"Hểc":428," aq":275," at":395," as":1145," d ":2111," ba":20628," 가가":227," bi":39922," be":1810," bo":1086," bl":299," by":542," bu":1037," br":705," ca":18336," Xư":246,"Hể ":3004," Vư":1101," er":165," et":2265," es":168," en":1522," em":442," el":437," bà":2390," fe":289," bá":2320," fa":2087," eu":165," ex":489," fu":610," fr":2001," bí":964," bì":10908," fo":1760," bê":1224," bé":146," fl":771," fi":679," bã":190," ge":1821," cá":22553," câ":2231," cà":270," ga":2783," bú":206," bó":2103," cl":550," cm":154," co":7147," cr":532," ce":1064," ch":72993," ci":299," da":4945," cu":4863," cy":157," do":4301," dr":248," de":8416," di":19653," ec":238," ed":190," ea":304," du":2623," 三三":209," vù":22601," vă":2376," ví":173," vì":1170," võ":378," vô":1027," vò":489," và":46932," vâ":230," sĩ":1785,"ка":178," tù":416," tú":155," tô":909," nư":35851," tă":379," xo":207," tê":7377," nơ":1991," să":488," tò":331," xu":3665," tí":18540," tì":8960," mư":601," ww":167," só":461," sô":2005," tâ":11572," tà":3363," tá":3073," xe":994," xa":907," tư":4765," vũ":680," 三之":172," sư":822,"ов":213," yê":400," sơ":282," rư":159," vĩ":1312," xã":6617," xâ":941," xá":864," ru":574," nô":442," nó":3467," hư":1543," sa":4809," nú":1256," se":1352," sc":583," si":4586," sh":865," nă":29145," sn":2777," sm":592," sl":244," sp":4116," so":2264," qu":28552," mó":260,"ви":141," mô":1890," mù":492," ra":5117," re":1311," nà":32102," nâ":291," ri":1195," hơ":1747," né":300," ro":791," lĩ":607," nê":751," lò":161," pu":610," pr":1132," lí":1307," lú":446," s ":1052," lô":926," px":1128," py":148," mã":975," má":2233," mà":2646," lý":2654," mì":566," mé":12707," ot":153," kì":215," op":485," kí":1225," or":1862," lá":722," pe":891," là":155391," lã":1013," lâ":684," pa":1485," ký":784," lè":332," pl":606," po":832," lê":796," pi":462," ph":51377," wa":721," sâ":1031," sá":4080," we":797," rõ":266," y ":288," lư":3756," wo":408," wi":1339," wh":1197," sê":264," va":1100," ve":759," uy":141," vo":357," vu":12917," rã":285," vi":8649," ty":993," tu":4206," us":140," mũ":152," up":179," un":373," ta":1679," v ":243," sy":262," st":916," su":3809," lũ":299," tr":156052," to":6595," th":230858," ti":21975," te":899," đu":484," đa":1700," đe":474," đi":17419," đo":2466," Đá":164," Đà":1637," Đâ":3555," Đì":322," Đo":196," Đi":1416," Đa":443," đơ":1908," đư":29691," Đư":847," đí":392," đê":8032," đì":460," đá":3730," đâ":1604," đã":4347," Đă":188," đà":1035," Đô":12690," đă":220," đú":182," đô":27698," đó":3827," đĩ":596,"Lể ":569,"Lểi":178,"Lển":215,"Lểp":1280,"Lểc":1143," Bể":9869," Kể":5918," Hể":9143,"Kể ":5821," Gể":165," Cể":8663," Dể":757," Âm":150," Âu":2129," Îl":330," Ôn":1608,"Nể ":198,"Nển":165,"Nểi":1235," Úc":1243," Ý ":1274," áp":355," án":814," âm":3643," ít":431," ô ":353," ôn":1711,"Mể ":2527," ý ":503,"Mểc":807,"Mểt":1153,"Mểu":174,"Mển":285,"Mểi":146," ăn":626," 가":331," ươ":433," ưu":158,"가":830," hể":63957," gể":12621," lể":23214," kể":7585," cể":67038," dể":12218," bể":45724," Vể":1292," Tể":7366,"Rểp":306," Xể":142," Nể":1895," Lể":3615," Mể":5122," Rể":522," Sể":1093," vể":53702," xể":2191," yể":935," mể":131122," nể":21375," rể":4289," sể":54954," tể":83225,"Tểt":172,"Tểp":225,"Tểc":152,"Tểa":1075,"Tển":2741,"Tểi":245,"Tể ":2617,"Sể ":900,"Vểt":162,"Vển":442,"Vểi":163,"Vể ":500,"ưểt":382,"ưểu":183,"ưển":18802,"ưểm":9501,"ưểi":24657,"ưểc":67509," Để":19647," để":91683," ưể":501,"Ávi":245,"ال":152,"Áo ":1417,"三三 ":318,"三万 ":202,"Âu ":2118,"三专 ":318,"Âm ":149,"ươn":12134,"ươi":146,"가가":499,"Bể ":2169,"AO ":231,"AN ":149,"Bểt":140,"Bểc":4036,"Bển":2788,"Bểo":450,"Cể ":946,"Cểu":671,"Cểp":339,"Cểm":232,"Cển":5510,"Cểc":787,"Dể ":256,"Dểc":190,"Bà ":315,"Bá ":150,"Bài":310,"Bàn":152,"Bác":305,"Fel":162,"Fen":155,"Fer":312,"Fis":282,"Ext":290,"Fas":526,"Fal":176,"Far":151,"Fab":275,"Eri":170,"Ess":158,"Est":392,"Eth":271,"Eup":437,"Eur":1040,"El ":188,"Ele":184,"Eng":198,"Epi":248,"Ent":180,"Các":1801,"Ger":929,"Cát":277,"Geo":862,"Gen":359,"Gla":140,"Gha":245,"Gia":2324,"Gil":159,"Gir":424,"oể ":155,"oểt":2492,"Cá ":259,"oểc":3719,"Gan":147,"Gal":295,"Gam":240,"Gau":147,"Gar":1513,"oển":3941,"oểi":4411,"Gab":195,"Fus":252,"Fro":378,"Flo":588,"Fla":166,"Fle":174,"ũi ":200,"Fra":932,"Fri":349,"ũng":2953,"Fre":553,"Bín":197,"Bìn":1748,"Fon":217,"For":497,"Fou":186,"Dân":1220,"nểu":216,"II ":1176,"Hil":320,"Him":177,"Hin":145,"Hip":145,"nể ":1462,"Hel":390,"nểi":2679,"Hei":256,"nểm":15373,"nển":1144,"Hem":163,"Hen":196,"Hes":405,"nểa":304,"Her":528,"Cúp":236,"Hal":332,"Hai":401,"Han":467,"Ham":344,"Has":179,"Har":748,"Haw":533,"Hau":3745,"Côt":1585,"Guy":153,"Cô ":190,"Gua":732,"Có ":275,"Gui":1036,"Côn":1681,"Gre":1012,"Gri":151,"Gra":2331,"Gro":483,"Glo":169,"Giá":926,"Gon":156,"Goo":205,"Gol":188,"Gom":158,"Úc ":1233,"Inn":161,"Int":561,"Ins":197,"Ill":204,"Ind":2106,"mểc":13680,"mểm":11638,"mểi":2779,"mểu":420,"mểt":99606,"mển":1814,"mể ":1110,"Ibe":205,"亞 ":440,"Hyp":280,"Hyd":396,"Dôm":338,"Hy ":979,"Hun":464,"Huy":2731,"Hue":217,"IV ":160,"Hoà":1902,"Hor":294,"Hou":153,"Hom":153,"Hon":555,"Hok":148,"Hol":1270,"Hoa":8475,"Arg":562,"Are":201,"Arc":363,"Ard":1593,"Ara":960,"Arm":257,"Ari":480,"Aqu":1651,"Apo":203,"Ath":149,"Atl":649,"Ast":281,"Ass":392,"Asi":256,"Arr":175,"Art":235,"Ave":196,"Auv":549,"Aus":949,"Aur":157,"Aud":253,"Aug":204,"Aub":473,"lể ":2800,"Azu":1003,"lểp":5146,"lểt":155,"lểi":2389,"lển":5223,"lểa":430,"lểc":6489,"Ba ":889,"lểy":462,"Bai":215,"Bal":574,"Ban":6419,"Bac":146,"Bad":1148,"Bay":966,"Bar":929,"Bat":270,"Bas":1136,"Bau":155,"Abr":165,"Aca":233,"Acr":321,"Ach":200,"Ade":163,"Ai ":341,"Aga":200,"Afr":687,"Afg":186,"Air":488,"Ala":309,"Alb":681,"An ":1388,"Alg":185,"Ali":170,"Ale":299,"Alv":153,"Als":515,"Alt":493,"Alm":187,"All":366,"Alp":2942,"Ame":689,"Amb":210,"Ama":449,"Amp":158,"Anh":5927,"Ang":642,"Ana":331,"And":666,"Ant":595,"Ano":159,"Ann":219,"Bus":168,"Bul":625,"Bur":1284,"Buc":492,"Bru":412,"kể ":5372,"Cab":144,"kểt":1768,"Cae":179,"Cal":3283,"Cam":1757,"Cai":141,"Cas":3059,"Car":1359,"Cau":236,"Cat":533,"Cao":644,"Can":1671,"kểc":374,"Cap":594,"Bea":394,"Ber":1074,"Ben":559,"Bel":748,"Bin":143,"Bil":278,"Bis":150,"Bit":253,"Bir":234,"Blu":260,"CP ":196,"Biê":192,"CN ":900,"Bla":380,"Bre":721,"Bra":1413,"Bro":439,"Bri":863,"Bol":471,"Boi":232,"Bon":251,"Bor":635,"Bos":277,"Bot":225,"Bou":1517,"Cyp":409,"Cur":167,"Cub":268,"Cun":184,"Cup":164,"EE ":154,"Des":235,"Deu":424,"Del":231,"Dem":185,"Den":364,"Dam":166,"Dan":842,"Dar":270,"Dav":172,"Dal":154,"Cho":474,"Chr":351,"Che":539,"Chi":4142,"Cic":417,"Chu":975,"Cit":157,"Châ":2351,"Cle":204,"Cla":633,"iểt":19441,"iểu":22084,"iểy":197,"Cel":188,"iểm":11357,"iểp":3887,"iển":94986,"Cen":1295,"Cer":828,"iểc":3158,"iểi":7620,"iểa":1763,"Cha":5749,"Cri":167,"Cra":378,"Cre":395,"Chư":286,"Cro":546,"Chù":202,"Chú":672,"Chí":1230,"Coc":220,"Coe":184,"Cop":262,"Cos":1089,"Cor":1423,"Com":752,"Col":1893,"Con":3653,"Cou":867,"FA ":242,"Drô":335,"iể ":1731,"Edw":139,"Ông":1552,"Ect":200,"Ecu":469,"Eas":364,"Do ":273,"Diê":175,"Dic":144,"之三三":139,"Dit":152,"Dis":351,"hểo":739,"hểp":5189,"hểm":3873,"Dip":407,"hển":23819,"Dio":154,"hểy":11164,"hểu":6003,"Die":258,"hểt":14285,"hểa":1704,"hểi":18265,"hểc":23691,"Di ":179,"hể ":155404,"Dun":239,"Duy":294,"Du ":216,"Dri":386,"Dre":146,"Dra":192,"Dou":158,"Don":392,"Dom":257,"Dor":723,"Cươ":311,"Nev":160,"Neu":541,"Net":191,"Nep":895,"Neo":280,"Nas":316,"Nat":595,"Nav":156,"Nig":396,"Nie":1241,"Nic":337,"Nin":1068,"Nhi":250,"Nha":5926,"Nga":1678,"Ngh":1164,"Ngu":2389,"Ngo":273,"New":2499,"Myr":349,"xể ":903,"Mya":329,"Nak":165,"Nam":11941,"Nan":196,"Nag":208,"Na ":357,"xểp":906,"xểy":267,"Như":191,"Nym":236,"Nhó":149,"Nhà":676,"Nhâ":3285,"Ngô":642,"Ngà":567,"Ngâ":218,"Ngư":724,"Nhĩ":654,"Nov":205,"Ngũ":256,"Nor":4126,"Not":381,"Nob":171,"Noc":1779,"Oec":143,"Dươ":1846,"PG ":211,"Ois":715,"Ohi":151,"Oah":152,"Occ":238,"Obe":662,"Île":330,"Ott":171,"Ovu":166,"Kôn":235,"Oly":147,"Oli":201,"Giể":2035,"Ont":199,"Or ":550,"Opo":183,"Ora":158,"Ore":369,"Orc":304,"Ori":453,"Orn":566,"Ost":243,"Phú":926,"Phù":169,"Phò":192,"Phó":180,"Phá":21296,"Ple":538,"Phâ":188,"Pla":641,"Hiể":1343,"Lê ":891,"Pin":370,"Pit":142,"Phy":669,"Pie":506,"Pic":810,"Pho":672,"Phi":3036,"Pha":566,"Lãn":143,"vểy":569,"Lâm":707,"vển":2537,"vểt":17681,"Pfa":1704,"vểa":164,"vểc":13644,"vểi":7805,"Per":956,"Pet":409,"Pen":544,"Pel":140,"Lào":383,"vể ":11302,"Pay":1416,"Là ":298,"Pat":164,"Pas":888,"Par":1717,"Pau":274,"Pac":219,"Pan":548,"Pap":721,"Pal":1091,"Pak":192,"Pyr":3193,"Huể":468,"Pte":513,"Pun":221,"Pup":166,"Pue":171,"Puy":394,"Pro":2087,"Pri":425,"Pre":247,"Phư":678,"Pse":388,"Hoể":173,"Pra":808,"Pol":756,"Pom":148,"Pon":298,"Poi":1472,"Pot":227,"Por":309,"uểc":63038,"uểi":2825,"Lăn":196,"uểt":6647,"uển":17332,"Mã ":868,"uể ":2223,"Lý ":659,"Mùa":206,"SA ":174,"Ram":194,"Ran":617,"Quá":225,"Quâ":725,"Môn":650,"Quý":277,"Qua":706,"Qui":159,"Que":829,"Quy":457,"Ita":500,"Isl":594,"Isr":263,"It ":1456,"Ira":481,"Ire":363,"Isè":447,"tểm":507,"tển":38505,"tểi":9573,"tểc":3283,"tểa":923,"tể ":24294,"Jac":218,"Jav":319,"Jan":148,"Jam":357,"tểo":2243,"tểp":1747,"tểt":2043,"Jer":195,"Jea":217,"Biể":504,"Jos":191,"Jor":166,"Joh":334,"Jul":480,"sể ":37621,"sển":14954,"sểm":218,"sểc":1290,"sểa":158,"Kai":155,"Kam":181,"Kal":268,"Kan":358,"Kau":180,"Kat":153,"Kas":184,"Kar":496,"Kaz":203,"sểt":255,"sểp":188,"Ken":722,"Kir":203,"Kit":143,"Kin":907,"Kim":609,"Kho":491,"Khu":1438,"Kha":464,"Khi":230,"Chể":1285,"Khê":158,"Khá":594,"Khô":380,"Kon":253,"Kor":151,"Kre":398,"Gòn":201,"Cuể":281,"Kus":145,"Kur":182,"Hàn":1241,"Leu":183,"Les":367,"Lep":631,"Leo":339,"Len":152,"Hán":6856,"Lei":182,"rểc":1530,"Lea":285,"rển":39207,"rểm":291,"rểi":1137,"Hà ":2463,"Lau":510,"rể ":6793,"Le ":619,"Lak":163,"Lai":390,"Las":248,"Lat":742,"Lar":215,"Lao":140,"Lam":368,"Lan":4696,"Lac":165,"Lab":180,"倉 ":180,"La ":2717,"Liê":1950,"Hér":279,"Diể":335,"Lib":574,"Lie":155,"Lig":183,"Lim":511,"Lin":692,"Lio":171,"Lis":148,"Lit":507,"Liv":154,"Leó":2050,"Hãn":333,"rểt":1287,"Hòa":572,"Lud":184,"Luc":212,"Loà":1669,"Hìn":160,"Loz":163,"Lou":367,"Los":193,"Lot":580,"MS ":483,"Loi":3201,"Lor":2131,"Lon":1378,"Lom":271,"Loa":517,"Ma ":267,"Hóa":437,"Luâ":253,"Lyc":258,"Mei":187,"Men":179,"Mel":544,"Mes":227,"Mer":503,"Meu":1122,"Met":367,"Mec":579,"Meg":242,"Med":321,"Mex":918,"Man":2248,"Mal":1668,"Mar":4888,"Mas":469,"Mag":297,"Mad":710,"Mah":444,"Mai":1077,"Mac":532,"NE ":2847,"May":519,"Mau":531,"Mat":259,"Miê":150,"Mol":400,"Mon":1606,"Mos":1419,"Mor":654,"Mou":470,"Mot":424,"Moz":414,"Mid":2002,"Mic":1239,"Cơ ":351,"Mit":747,"Mir":161,"Mis":522,"Mil":319,"Min":1719,"Mun":171,"Mur":1848,"Mus":259,"Xià":174,"Phể":1906,"Tây":8477,"Tân":1027,"Tào":168,"Tàu":164,"Süd":288,"Sôn":404,"Sóc":214,"Wor":462,"Wol":216,"Séc":256,"Sèv":318,"Whi":209,"èvr":358,"Wik":174,"Wil":393,"Win":429,"Wie":149,"Wit":233,"ère":1422,"Sài":216,"Web":172,"Wei":433,"Lươ":358,"Wes":961,"Sân":446,"Was":264,"War":327,"Wal":818,"ès ":590,"Lưu":290,"Dưể":277,"èn ":152,"èo ":278,"ém ":263,"之丁":166,"QĐ ":168,"之三":478,"之万":178,"ée ":472,"之专":315,"之之":217,"ées":2904,"Vos":497,"Vor":516,"Vol":589,"éc ":283,"Nhể":3766,"Ngể":811,"Viê":165,"évi":139,"Tĩn":188,"ép ":1113,"Zea":402,"Zar":282,"Zam":723,"én ":239,"éo ":609,"éra":396,"ét ":23407,"éri":203,"éné":2942,"Zim":303,"Zel":153,"épa":1146,"Vân":484,"ên ":47944,"êm ":9120,"Yps":167,"Quể":10633,"Yve":176,"並三":153,"Sĩ ":505,"Yor":442,"You":143,"Yon":155,"ênh":268,"êng":589,"专专":219,"专三":225,"êu ":3625,"Yel":146,"三万":220,"三丁":213,"三三":777,"三专":394,"Tô ":277,"Xuâ":498,"三之":347,"Tôn":652,"Túc":179,"丁专":144,"丁丁":142,"Tên":660,"丁三":258,"Tín":160,"丁之":215,"Xuy":470,"ãi ":669,"Syn":143,"Syr":151,"Swi":186,"Swa":238,"Sur":243,"Sum":294,"Sul":327,"Sun":218,"Sud":207,"Str":573,"Stu":169,"Sti":380,"Sto":266,"Sta":800,"Ste":1346,"Ten":237,"Tel":150,"ãnh":975,"ãng":1319,"ão ":484,"Tam":802,"Tan":929,"Tas":235,"Tar":601,"ãn ":565,"Tai":151,"Tak":148,"Ski":144,"ãy ":559,"Khể":614,"Shi":359,"She":144,"Năm":661,"Sho":220,"Sha":353,"Sim":166,"Sil":271,"Sin":736,"Sie":417,"Sib":258,"Sic":157,"Ses":155,"Ser":590,"Sen":317,"Sel":193,"Hươ":208,"Sei":684,"Seg":435,"Sri":344,"TV ":172,"Spa":202,"Spi":140,"Sph":1036,"Spe":218,"Spr":184,"Sou":1403,"Sol":431,"Som":283,"Son":366,"Sor":294,"Kiể":703,"Slo":396,"Nôn":230,"Rus":514,"Nó ":10964,"Sai":3614,"Sam":307,"Sal":1166,"Saa":431,"Sac":786,"Sab":139,"Sco":422,"Sci":154,"Sch":2083,"Sca":289,"Sax":162,"Sav":348,"Sat":196,"Sau":596,"Sar":1013,"Sap":212,"San":1415,"Sao":173,"Hưn":444,"Sa ":225,"TA ":219,"Res":158,"Rhi":678,"Rhe":1850,"Riv":248,"Ris":546,"Rie":160,"Ric":612,"Red":234,"Rei":173,"Reg":216,"Ren":178,"Rep":253,"Rob":306,"Roc":356,"Rou":1296,"Rot":151,"Ros":295,"Rom":626,"SS ":368,"Rhô":1640,"Ven":831,"Vau":301,"Van":289,"Val":1014,"Var":300,"Vic":424,"Vie":766,"Vir":376,"Vil":850,"Vin":383,"Ver":694,"Vex":266,"Ukr":405,"Uni":646,"Miể":206,"Uy ":300,"Utt":447,"Tră":223,"Luể":194,"Trá":373,"Trà":189,"Trâ":155,"Trì":245,"Bưể":300,"Trư":1573,"Uga":441,"Tex":717,"Ter":1194,"Tha":1705,"The":9028,"Thi":2418,"Tho":351,"Thu":1030,"Til":178,"Tim":168,"Tin":432,"Thà":2636,"Thá":3215,"Liể":150,"Thü":723,"Thô":412,"Tiê":963,"Tor":743,"Tok":152,"Tol":222,"Tom":166,"Tou":295,"Thư":1102,"Tru":10246,"Tro":2116,"Tri":2061,"Tre":371,"Tra":816,"Toà":178,"Tuy":629,"Tur":1442,"Tun":141,"Mưể":195,"ày ":41264,"Tươ":169,"àu ":3188,"gểa":154,"gểc":1587,"gểi":5837,"gểp":336,"gểm":3968,"gển":2170,"gểy":212,"gểt":591,"ành":21823,"àng":7133,"gể ":2467,"ào ":9552,"àn ":5519,"àm ":2556,"ài ":40596,"dể ":1928,"bis":208,"bit":429,"biu":210,"bio":195,"biq":379,"bir":196,"bil":353,"bin":1156,"bii":441,"dểa":1072,"dểc":2450,"bo ":249,"dểi":171,"dểm":153,"dển":5451,"dểu":482,"dểy":237,"áy ":2251,"blo":143,"ble":788,"bli":464,"bla":343,"boa":544,"bol":192,"biê":756,"bon":625,"bom":252,"bop":200,"bor":571,"bot":181,"bos":169,"bou":707,"bbe":548,"be ":978,"áo ":4269,"ban":14532,"bal":489,"bai":195,"bac":1588,"bad":244,"bab":362,"án ":11049,"bay":2258,"bat":528,"bas":507,"bar":886,"bao":2943,"bea":250,"áp ":27496,"ánh":4002,"áng":13329,"bi ":208,"bei":269,"bee":755,"bed":546,"bec":391,"ber":5184,"ben":538,"bel":1263,"bek":171,"bes":289,"bet":259,"bfa":299,"áu ":550,"bia":2262,"bic":185,"bid":364,"át ":6081,"ách":6363,"áce":165,"ái ":6094,"ca ":5266,"car":2682,"cas":523,"cat":809,"cau":258,"can":2819,"cao":13635,"cap":271,"cac":552,"cae":343,"cad":152,"cam":352,"cal":1785,"cai":449,"ce ":3602,"ám ":1096,"bri":1032,"bro":469,"bra":914,"bre":597,"bru":440,"bsi":207,"bur":2940,"bul":333,"bun":198,"bum":722,"but":706,"bus":353,"by ":708,"bwe":288,"ác ":24475,"aka":675,"am ":27480,"ake":553,"aki":591,"akh":416,"aji":229,"ajo":231,"al ":6772,"aja":635,"aii":453,"ail":3696,"ain":10996,"air":827,"ais":1435,"ait":246,"ak ":354,"aig":201,"aid":285,"aic":180,"aia":148,"ây ":27201,"ahi":144,"ahu":249,"ahr":141,"aho":292,"aha":852,"agi":293,"agr":420,"agu":637,"agn":2270,"ago":1655,"aq ":141,"anu":911,"anz":946,"any":498,"ano":1266,"ann":1274,"anm":363,"ant":5267,"ans":1570,"ane":1647,"ang":23334,"anh":11504,"ani":4224,"anj":313,"ank":983,"ap ":200,"ana":4781,"anc":3852,"and":17225,"amu":239,"amm":581,"amo":823,"amp":3495,"ams":266,"ami":3273,"ame":2454,"amb":1921,"ama":1996,"ao ":21236,"alz":1868,"aly":679,"alv":524,"alu":519,"alt":1192,"als":583,"alp":280,"alo":1138,"alm":374,"all":4541,"alk":430,"alg":162,"ali":4610,"alc":275,"ald":946,"ale":3407,"alf":143,"ala":5532,"alb":1038,"an ":27435,"aku":180,"ako":211,"aba":1197,"abe":439,"abi":699,"abl":307,"abo":447,"abr":553,"abu":216,"abw":286,"ae ":31054,"aca":592,"aal":305,"aar":275,"ad ":1523,"ac ":1152,"âng":210,"ab ":257,"aft":152,"aff":222,"ai ":10857,"aga":1564,"age":954,"aeo":180,"aen":693,"ael":524,"aes":144,"aer":162,"Vươ":859,"aei":212,"ah ":482,"âte":406,"ado":1640,"adr":334,"adi":656,"âu ":6939,"ade":2368,"aea":378,"aec":197,"ag ":159,"ady":140,"adt":318,"adu":484,"aco":486,"ack":866,"aci":2053,"ach":4974,"ace":5973,"acc":246,"ada":2077,"af ":167,"act":895,"acu":424,"acr":438,"azo":203,"azi":604,"aze":208,"aza":466,"axi":240,"axo":326,"az ":215,"ayo":158,"ays":2306,"aya":1069,"aye":1477,"ân ":71107,"ba ":1967,"âm ":6828,"aqu":368,"at ":2191,"arh":179,"arg":1494,"are":4513,"ard":3817,"arc":1390,"arb":768,"ara":4118,"arp":777,"aro":1967,"arn":2152,"arm":452,"arl":768,"ark":1469,"ari":8943,"aru":469,"arv":290,"arr":2293,"ars":863,"art":4067,"au ":6244,"asa":466,"ary":947,"arz":380,"asi":1358,"ash":1142,"asc":1250,"ase":497,"aso":213,"asp":226,"ask":259,"asm":354,"aon":161,"ar ":3587,"apa":481,"ape":779,"api":791,"aph":710,"apl":205,"apo":627,"app":349,"apt":205,"apu":632,"as ":6065,"ava":1308,"ax ":315,"aux":509,"auv":229,"aut":4199,"avo":316,"avi":854,"ave":987,"awe":151,"ay ":14622,"awa":1004,"awi":403,"ata":3801,"asu":225,"ast":6128,"ass":2666,"atr":716,"ato":1406,"ate":3193,"atc":165,"ati":4840,"ath":1382,"aua":167,"auc":575,"aub":164,"att":609,"ats":390,"atu":1696,"aty":238,"aul":975,"aum":254,"aun":342,"aur":1043,"aus":1014,"aud":522,"aue":262,"aug":153,"aui":145,"bể ":9115,"Wür":527,"bểy":259,"bểt":2371,"bểu":602,"bểi":3447,"bểo":909,"Xã ":2077,"bển":18106,"bểc":10801,"Thể":19271,"Tiể":1514,"Trể":2534,"Vĩn":400,"Xíc":159,"Võ ":184,"cểu":3163,"cểt":394,"cểp":4267,"cểc":593,"cểa":46999,"cển":3734,"cểm":741,"cểi":1406,"Hưể":237,"Vùn":202,"cể ":5697,"Văn":1172,"Sư ":192,"Viể":12501,"Vũ ":518,"Tư ":617,"Tuể":240,"Xô ":542,"Yên":481,"Sơn":1964,"ji ":324,"jar":408,"jan":213,"biể":38109,"jo ":152,"itr":907,"ito":2297,"itu":456,"itt":1509,"its":449,"itz":828,"ity":598,"ism":206,"isl":191,"iso":476,"isp":337,"iss":3448,"ist":3624,"ita":3373,"itc":146,"ite":2019,"ith":2136,"iti":2423,"ivo":162,"ius":1319,"ium":1206,"iva":362,"ix ":837,"ivi":819,"ive":1549,"ipo":143,"ipp":1792,"ipu":171,"ipt":450,"ipi":254,"iph":349,"ipl":287,"ilô":10662,"is ":16454,"ion":4473,"iop":856,"ior":202,"ios":885,"iot":545,"iou":177,"ioi":173,"iol":823,"ipa":1057,"ipe":657,"ir ":1809,"iru":298,"irs":241,"ück":162,"iro":773,"irk":203,"irl":235,"iri":455,"isi":750,"ish":1324,"ise":1480,"isc":1025,"isa":361,"iqu":1196,"ire":3687,"irg":448,"ira":1107,"irc":652,"it ":1527,"ja ":441,"iya":187,"iz ":244,"eón":2056,"가가가":272,"izo":396,"ize":388,"iza":272,"kim":1056,"kil":10715,"kia":494,"kin":3453,"kip":325,"kir":466,"kis":481,"km ":3828,"chể":21772,"ki ":1183,"khi":3505,"út ":627,"khe":165,"kha":834,"khu":15081,"kho":6571,"gày":9377,"gái":216,"kel":215,"ken":731,"kes":174,"ker":740,"ket":226,"key":304,"gân":416,"gây":413,"ke ":634,"úp ":776,"gàn":962,"úng":1614,"kra":492,"kre":255,"kt ":229,"cũn":2434,"ểa":61690,"ku ":366,"km²":641,"kot":155,"kor":174,"kom":159,"kok":195,"ks ":691,"ể ":376292,"úy ":216,"cũ ":497,"kno":896,"kka":183,"khô":4285,"khó":360,"khí":730,"khú":467,"ko ":151,"khá":4090,"kle":735,"kla":228,"buể":254,"ểo":9548,"ểp":25031,"ểk":175,"ểm":59218,"ển":369560,"ểi":112828,"ểc":255331,"ểy":15079,"ểt":179295,"ểu":43805,"kaz":157,"gà ":270,"kat":204,"kar":238,"kas":219,"kan":739,"kal":182,"kam":185,"kai":366,"ka ":1184,"cùn":1840,"cúp":216,"ha ":8300,"ùng":27727,"ham":3795,"han":4769,"hao":550,"hap":378,"hai":4690,"hal":2163,"hau":2057,"hav":347,"har":4673,"has":721,"hat":786,"hae":501,"hag":376,"hab":337,"had":177,"hac":331,"hay":7652,"he ":18327,"dàn":837,"dài":1594,"hel":1664,"hei":3775,"hec":208,"hed":210,"hea":373,"hey":228,"hev":147,"het":420,"hes":679,"her":2719,"heo":10006,"hen":1600,"hem":538,"hi ":13142,"dây":222,"dân":28557,"dãy":398,"căn":327,"hig":332,"hie":278,"hid":1412,"hic":705,"hia":1555,"hip":346,"hio":999,"hin":3454,"him":2986,"ùy ":240,"hil":2244,"hik":232,"hii":300,"hiu":173,"his":1013,"hit":572,"hir":444,"hn ":286,"hla":242,"hle":1267,"hli":520,"hlo":240,"ho ":7256,"hma":350,"gma":174,"go ":1433,"giá":5603,"gme":307,"già":408,"glo":256,"gle":536,"gli":276,"gla":529,"gko":162,"gog":725,"gny":420,"ghĩ":2919,"gno":258,"gni":256,"gne":3863,"giú":291,"gna":708,"úa ":604,"giô":172,"gs ":297,"goz":262,"úc ":3114,"gom":139,"gol":384,"gon":1688,"gos":596,"gor":601,"gov":334,"gu ":148,"goà":839,"gro":663,"gra":1031,"gri":527,"gre":280,"gto":303,"gui":371,"gum":182,"gul":499,"có ":47334,"gua":512,"gue":1969,"gy ":222,"cô ":368,"guy":4577,"gur":185,"gus":453,"gun":159,"còn":3275,"úi ":1356,"côn":4644,"gyr":164,"iai":626,"iam":328,"ial":1014,"iao":1227,"ian":5609,"ias":397,"iar":265,"iat":696,"ic ":3037,"iac":1407,"iae":280,"ibl":173,"ibi":314,"ibo":164,"ibu":345,"id ":1469,"iba":306,"ibb":546,"ibe":1206,"ia ":29704,"iet":540,"ieu":473,"iel":1226,"ien":2075,"ier":2747,"ies":4767,"ied":1831,"ieg":187,"ig ":1226,"ifo":1413,"iff":148,"ife":614,"ifl":166,"ifi":693,"icr":1054,"ics":295,"ict":897,"icu":1741,"ico":2316,"ick":622,"ici":3591,"ich":3932,"ice":765,"ie ":3741,"ica":6048,"idu":239,"ids":175,"ido":567,"idi":2598,"ide":2455,"ida":26239,"iid":4750,"il ":3121,"ija":174,"iji":157,"im ":5476,"ika":371,"ige":770,"iga":742,"ii ":1370,"igm":416,"igh":923,"igi":710,"igu":318,"igs":187,"igr":220,"igo":300,"ign":1169,"iha":223,"ik ":169,"imo":742,"imm":158,"imp":567,"ime":1906,"imi":643,"ip ":810,"inc":1322,"ind":1704,"ina":4704,"inb":264,"imu":305,"inn":513,"ino":1469,"int":4526,"ins":1803,"inf":237,"ine":10837,"inh":13778,"ing":8141,"ini":3074,"inl":2046,"ink":351,"ioc":292,"iod":167,"inu":932,"inv":156,"inx":181,"iny":208,"iko":368,"iki":420,"ike":257,"ila":1297,"ilb":181,"in ":13262,"ilo":550,"ill":9682,"ilh":181,"ili":3385,"ild":355,"ile":3779,"ima":1310,"imb":551,"io ":1175,"ily":2239,"ils":2324,"ilu":323,"how":204,"hol":800,"hom":456,"hon":2401,"hoi":164,"hos":411,"hot":229,"hou":479,"hoo":159,"hop":241,"hor":2606,"hoa":5214,"hof":203,"hoe":206,"hod":441,"hoc":207,"hni":161,"hne":266,"dée":277,"hme":233,"hmi":203,"hiê":5040,"dép":1137,"hua":252,"htt":326,"htr":324,"hth":197,"hte":186,"hst":227,"hse":1600,"hoá":860,"hoà":1969,"hu ":18061,"hry":423,"hro":1154,"hre":321,"hri":577,"ùa ":1067,"ht ":687,"hra":468,"hya":190,"huê":158,"hyl":1269,"dòn":604,"hy ":171,"hwa":665,"hwe":313,"hum":443,"hun":1586,"hus":902,"hut":182,"hur":289,"huy":20578,"Vưể":237,"dùn":1738,"dù ":368,"hyt":176,"hys":223,"hyr":202,"huô":174,"ùi ":234,"ffe":313,"ffi":237,"fer":812,"báo":721,"bác":152,"fen":465,"bán":1218,"fel":1035,"fgh":188,"bà ":200,"fas":191,"far":156,"fam":2105,"fal":2041,"bày":158,"bàn":328,"bào":422,"bài":1285,"ff ":218,"eya":142,"ext":206,"eyr":325,"eyh":211,"eye":179,"exa":986,"ez ":316,"exi":1325,"exc":181,"ezu":350,"ezi":175,"eta":842,"ete":743,"eti":1014,"eth":666,"etn":165,"etl":616,"esp":684,"esn":283,"eso":340,"est":3808,"ess":1434,"esw":957,"ev ":202,"euc":337,"eud":540,"eui":263,"eum":201,"eto":465,"etr":999,"ets":459,"ett":1071,"etu":203,"etw":156,"etz":312,"ew ":2560,"eve":622,"eva":566,"evi":1144,"euv":222,"eut":564,"eur":1318,"eus":1354,"ex ":606,"euz":190,"eux":671,"ey ":1664,"ewa":232,"erö":586,"epe":234,"epi":495,"eph":665,"er ":9592,"epa":418,"eot":213,"eor":527,"eom":471,"eol":262,"eop":530,"eon":709,"es ":26910,"ept":1404,"epu":235,"epo":154,"erk":202,"erl":752,"eri":6361,"erg":3169,"erh":199,"ere":2445,"erf":557,"erc":1171,"erd":573,"era":3401,"erb":858,"et ":4591,"equ":162,"esl":202,"esh":1269,"esi":2021,"esc":975,"ese":753,"eu ":303,"esa":259,"erz":260,"ery":556,"erv":528,"eru":1012,"erw":278,"err":2985,"ert":1566,"ers":4623,"ern":4630,"erm":2107,"erp":282,"ero":2376,"eki":196,"en ":12018,"elb":206,"ela":2654,"eld":1258,"elf":146,"ele":1267,"eli":1798,"elg":160,"elm":262,"elk":404,"ell":9746,"elo":933,"elu":208,"els":642,"elt":280,"ely":341,"eo ":10593,"eiß":164,"emb":1047,"ema":1158,"eme":2947,"emm":256,"emo":539,"emi":1585,"emp":238,"ems":155,"emy":139,"enf":291,"ene":1945,"enh":484,"eng":730,"enb":2082,"ena":1558,"end":2473,"enc":2127,"eno":956,"enn":3389,"enk":343,"enl":192,"eni":2073,"enu":1664,"ens":4503,"ent":10489,"enr":274,"enz":420,"eny":515,"eoc":157,"ego":1228,"ege":478,"egg":139,"egi":670,"egr":229,"egu":327,"ek ":217,"eic":752,"eis":833,"eir":787,"eim":1035,"eil":952,"ein":4903,"eie":545,"eid":730,"eig":203,"eif":191,"el ":3452,"eiz":186,"eit":258,"em ":1658,"öst":587,"giu":194,"gis":185,"gil":310,"gin":1363,"gio":553,"gid":1547,"gic":199,"gia":8820,"ght":794,"băn":187,"gho":161,"ghi":3850,"ghe":189,"gha":488,"ggi":146,"gge":165,"câu":470,"cây":1629,"gi ":387,"gen":5062,"cán":798,"cáo":198,"ger":1519,"ges":1085,"gh ":607,"các":18946,"geb":333,"cái":701,"gem":243,"gel":544,"cá ":1776,"ge ":1808,"gae":147,"gai":1612,"gas":1474,"gar":1812,"gau":202,"gat":452,"gay":317,"gam":376,"gal":707,"gan":1692,"gap":295,"ga ":2819,"bút":167,"Tưể":239,"fur":264,"fus":239,"bón":2056,"ful":164,"fun":375,"ft ":439,"fra":309,"fre":507,"fri":815,"bín":794,"fro":1604,"fou":879,"for":2385,"fon":152,"fol":504,"bìn":10852,"bên":1143,"bí ":160,"fle":146,"fla":250,"fli":289,"flo":441,"fly":418,"fic":547,"fie":487,"fil":195,"fin":314,"fis":489,"da ":3697,"de ":8611,"dac":762,"dad":140,"dal":972,"dai":189,"dag":446,"dae":24708,"dat":480,"dar":398,"dap":183,"dan":4922,"dam":377,"cun":718,"cul":2298,"cum":328,"cua":546,"cty":284,"ctu":2164,"ctr":238,"cto":873,"cti":1458,"cte":647,"cta":670,"cy ":251,"cus":673,"cur":399,"cut":255,"cyc":140,"cks":263,"cki":166,"ckl":786,"cla":486,"chá":201,"cle":346,"châ":14860,"cky":262,"chí":8076,"chò":225,"clu":420,"chó":180,"cli":182,"ché":314,"chì":193,"clo":464,"chù":312,"co ":1548,"chú":1406,"coi":717,"cod":256,"coa":287,"cob":146,"coc":214,"con":3655,"col":1035,"com":2135,"cor":1035,"cos":565,"cop":801,"cot":443,"cou":1134,"coz":183,"cs ":366,"ct ":454,"cre":241,"cra":438,"chơ":592,"cri":479,"cro":1725,"chư":1623,"ccu":244,"cci":838,"cco":265,"cca":156,"cea":4824,"ch ":37737,"cer":1071,"ces":531,"cet":142,"cen":1512,"cep":386,"Xươ":220,"cel":1002,"ced":395,"cha":3033,"chw":543,"chu":6009,"chy":360,"cia":1452,"ck ":1564,"cie":3416,"cid":2524,"che":4294,"chl":1776,"chi":13490,"cho":7644,"chm":217,"chn":259,"chs":1959,"cht":448,"chr":711,"cil":2248,"cif":277,"cis":311,"cit":448,"cin":1085,"cio":750,"cip":1009,"cm ":153,"cke":753,"ed ":4935,"eba":285,"ebe":884,"ôn ":3722,"ebi":183,"ebo":301,"ebr":934,"ebs":216,"ebu":294,"ec ":362,"eac":334,"ôm ":271,"eag":170,"eaf":201,"eae":4646,"ead":460,"ean":1098,"eal":621,"ear":1037,"eas":698,"eat":882,"eau":1120,"eb ":303,"ea ":3947,"efo":223,"efe":249,"ei ":970,"ega":773,"een":1179,"eel":145,"eed":257,"ees":218,"eer":175,"eep":145,"eet":728,"edi":1118,"ede":1955,"ône":1757,"ông":42975,"eda":404,"eg ":341,"edt":284,"edo":1988,"edr":212,"eck":1046,"ech":639,"eci":3537,"ece":167,"eca":304,"ee ":1150,"ôme":730,"ecu":225,"ect":1210,"eco":767,"dwi":249,"dwe":183,"dwa":258,"dy ":278,"dur":468,"dus":275,"duy":1143,"ôi ":2569,"dor":2168,"dop":306,"don":2791,"dom":306,"dol":520,"dow":395,"dov":304,"dou":172,"dos":360,"ds ":1070,"doa":646,"doc":1372,"dog":488,"dun":458,"dul":398,"duc":230,"dri":731,"dra":523,"dt ":665,"dre":808,"du ":1084,"dro":986,"dha":326,"dge":229,"dic":469,"did":312,"dia":1872,"ôte":1594,"der":3477,"des":3199,"ômé":10659,"dea":701,"ded":323,"dec":231,"del":1465,"den":4157,"dem":911,"deo":220,"di ":3427,"dle":656,"dla":192,"do ":4210,"diu":260,"din":1244,"dio":353,"dis":2108,"dit":379,"die":2847,"dil":249,"rgy":150,"rgu":287,"rhe":221,"rha":208,"rho":196,"rga":532,"ri ":2301,"rgi":1202,"rgh":152,"rge":1773,"rgo":1290,"rgn":567,"ret":1055,"res":3724,"rev":398,"reu":912,"rex":297,"rey":288,"rfa":190,"rfl":255,"nân":179,"rdu":164,"rds":270,"rdr":159,"này":31504,"rg ":4949,"reb":939,"rea":2006,"ree":1006,"ref":247,"rec":523,"red":781,"rei":1635,"reg":1203,"rem":776,"ren":4076,"rel":1428,"rer":300,"reo":199,"rep":265,"rf ":1207,"rda":570,"rcu":715,"rct":554,"rdo":799,"nào":548,"rdi":1755,"rde":2543,"re ":9446,"rbu":335,"rco":417,"rci":274,"rch":1874,"rce":427,"rca":280,"ray":496,"raz":574,"rd ":2860,"rao":655,"rap":552,"raq":160,"rar":494,"ras":1804,"rat":1838,"rau":875,"rav":215,"rbi":1026,"rbo":389,"rba":580,"rbe":418,"rai":3535,"rah":190,"rag":1656,"ran":8266,"ram":1112,"ral":2485,"rak":217,"rab":584,"raf":217,"rae":749,"rad":1615,"rac":3183,"rpu":270,"rpo":754,"rs ":2330,"rpe":165,"rpa":404,"rpi":173,"rph":340,"ror":201,"ros":1675,"rot":1221,"rom":2423,"ron":57984,"lĩn":607,"roo":669,"rop":3656,"roy":149,"rou":1200,"rov":1781,"row":593,"rob":744,"roa":358,"rod":644,"roc":1935,"roi":481,"rol":951,"rof":216,"rog":648,"nên":713,"rno":358,"rns":159,"rna":1180,"rne":2695,"rni":1419,"riè":172,"ném":189,"riê":408,"rmo":497,"rms":184,"ro ":929,"rma":3617,"née":2905,"rme":709,"rmi":637,"rly":155,"rlo":157,"rli":457,"rld":399,"rle":351,"rla":627,"rn ":3576,"hơn":1695,"hơi":801,"rki":204,"rke":393,"rka":202,"né ":169,"rm ":302,"riz":418,"rix":394,"rl ":161,"rip":365,"rio":1072,"rit":3591,"ris":2983,"riv":318,"riu":456,"rig":1218,"rii":3008,"ril":1020,"rin":4090,"rim":450,"ria":5391,"rib":1175,"ric":5324,"rid":4461,"rie":2155,"rif":320,"rk ":1670,"hơ ":851,"rwe":155,"nói":685,"rz ":208,"hư ":5084,"nôn":377,"rya":216,"ryc":442,"rug":231,"rue":707,"ruc":377,"rup":171,"run":25178,"rum":705,"rul":242,"ruy":2675,"ruz":213,"rus":1414,"rva":295,"rvi":473,"rve":224,"rwa":347,"ry ":2417,"rsi":891,"rso":252,"roß":201,"rsc":361,"rsd":187,"rsa":1123,"rsb":257,"rsh":319,"rse":899,"rta":737,"óc ":726,"rst":546,"rto":415,"rtb":145,"rte":1749,"rth":2805,"rti":1215,"nó ":2643,"rub":265,"rts":371,"rtr":430,"rtu":180,"rtt":513,"rt ":1957,"óa ":2701,"rqu":185,"rro":1564,"rrh":197,"rri":1788,"rre":2216,"rra":3074,"ru ":477,"rry":300,"rru":147,"sab":140,"sac":1864,"sai":281,"sak":172,"sal":439,"sam":384,"sba":297,"sbe":425,"sao":776,"óng":4090,"san":1255,"sau":2887,"sat":228,"sas":328,"sar":660,"oà ":337,"óp ":288,"sa ":2015,"núi":1191,"óm ":1521,"ón ":2564,"rze":166,"hưa":582,"rys":387,"ryo":172,"ryp":167,"ryl":162,"ói ":993,"ryn":172,"hưn":1523,"sha":619,"năm":27971,"năn":1182,"sho":293,"shr":233,"sht":381,"she":876,"shi":1264,"si ":634,"oãn":159,"sge":580,"sie":368,"sid":739,"sic":687,"sia":3700,"sk ":591,"shw":300,"shu":294,"sit":709,"sis":3021,"sip":265,"sin":5091,"sio":465,"sil":1895,"sim":553,"sii":258,"sif":151,"sig":220,"scr":307,"scu":281,"òng":2223,"oài":34230,"oàn":5706,"sdo":465,"sbu":460,"se ":4575,"oá ":380,"sca":1351,"sce":236,"sci":1194,"sch":1792,"sco":719,"sey":198,"ser":1028,"ses":272,"set":418,"oát":273,"seu":551,"sh ":1939,"sfe":321,"sea":715,"sei":161,"see":284,"sed":245,"sec":229,"sep":202,"sen":3196,"oán":1638,"sem":1371,"sel":2101,"hươ":4318,"spo":375,"shū":247,"spr":259,"sph":157,"spe":3907,"spi":1229,"spa":351,"sot":292,"sou":945,"sol":467,"som":376,"son":1789,"sop":308,"sor":191,"sof":194,"soi":556,"soc":217,"su ":286,"sra":294,"st ":2960,"squ":256,"ss ":872,"sli":218,"sky":167,"kiể":2684,"sla":1569,"sle":323,"ski":288,"sks":212,"khể":3237,"ska":369,"sna":2980,"sni":207,"sne":250,"smo":583,"siê":264,"so ":947,"sma":1028,"smi":179,"swi":1048,"syn":165,"syl":224,"sse":3231,"soá":206,"ssa":1676,"sso":1413,"ssi":3339,"ssu":544,"ste":5951,"stf":168,"sth":161,"sta":3335,"sto":2068,"stp":174,"sti":4685,"stl":165,"stu":445,"str":4349,"sts":262,"sty":144,"sub":863,"sul":490,"sum":304,"sup":191,"sun":266,"sus":998,"sur":1961,"suy":191,"òa ":5602,"sy ":172,"swa":243,"tai":3180,"tak":236,"tal":2442,"tae":263,"tag":338,"tah":173,"tab":252,"tac":777,"tad":502,"tay":436,"tax":151,"tau":185,"tat":1298,"tas":231,"tar":1441,"tap":149,"tan":2995,"tam":442,"tch":446,"òm ":317,"te ":8300,"tbu":170,"òn ":4112,"ta ":6742,"ký ":793,"ozè":153,"pa ":420,"làm":1846,"làn":610,"lá ":624,"pe ":1111,"par":2272,"pat":396,"pas":155,"là ":152991,"pac":448,"pag":1801,"pal":1430,"pan":1032,"phe":584,"pha":2087,"phu":325,"phr":290,"pho":3352,"phn":208,"phi":5842,"pi ":273,"lãn":895,"ph ":150,"lâu":392,"lâm":192,"pea":417,"pec":3297,"ped":468,"pen":678,"per":2665,"pet":646,"pes":3121,"pel":638,"pla":748,"hiể":23255,"pli":245,"phâ":2752,"phá":7538,"ple":773,"lès":368,"phí":12064,"phê":328,"plo":417,"phé":481,"phò":631,"phó":453,"phy":787,"pia":524,"pid":686,"pic":879,"pie":144,"pil":547,"pin":2627,"pio":231,"pir":455,"pis":429,"pit":358,"por":1000,"pop":359,"pot":426,"pos":699,"pom":618,"pon":447,"pol":658,"poc":162,"pod":1012,"ps ":851,"hū ":248,"ppi":1358,"ppo":224,"ppe":777,"phú":224,"po ":176,"lí ":1217,"lên":761,"pta":227,"pse":181,"psi":853,"pso":273,"ptu":208,"pua":385,"pub":253,"puc":309,"pte":1527,"pti":1324,"pto":542,"ptr":151,"pra":304,"hoể":8808,"pt ":251,"phư":1981,"pri":732,"pre":749,"pro":835,"huể":53256,"lôn":185,"lôm":10657,"pur":817,"pus":345,"pun":212,"pul":573,"lô ":685,"px ":1130,"pyr":166,"lý ":2650,"lúc":371,"mà ":1433,"màn":167,"máy":1955,"mã ":867,"màu":877,"mét":23053,"méo":221,"mìn":517,"qua":5837,"mô ":773,"quy":3085,"que":2033,"qui":2180,"món":229,"môn":561,"môi":520,"quâ":3680,"quá":966,"quê":311,"quý":155,"mùa":374,"ra ":16536,"ngo":2830,"ngi":1741,"ngl":604,"ngk":252,"ngu":5422,"ngr":255,"ngt":407,"ngs":604,"ni ":1381,"nge":3237,"ngh":7783,"nga":2179,"nho":251,"ndé":306,"nhu":514,"nha":2433,"nhi":5815,"nhe":263,"neg":239,"nei":512,"nel":1599,"nen":680,"nem":262,"neo":282,"ner":1201,"net":904,"nes":4373,"nev":164,"neu":463,"ng ":357107,"nea":1462,"neb":278,"nec":300,"ned":346,"nee":182,"nfo":163,"ney":270,"nez":428,"nh ":132657,"nfe":333,"nct":449,"nco":534,"nci":1276,"ncl":257,"nce":3207,"nch":2383,"nca":570,"ne ":19277,"nbu":1513,"ndu":416,"ndr":1581,"nds":990,"ndo":2398,"ndl":619,"ndh":176,"ndi":4609,"nde":3318,"nda":1999,"ncy":170,"nal":1151,"nam":13111,"nan":913,"nar":774,"nac":1244,"nad":927,"nae":1024,"nag":697,"nai":3249,"nbo":145,"nbe":462,"nd ":12230,"nba":380,"nav":164,"nau":516,"nat":2078,"nas":580,"nay":2459,"na ":6835,"iúp":291,"가 ":328,"cư ":415,"iôn":176,"myc":163,"nya":523,"nyi":193,"nz ":267,"ny ":1333,"nvi":479,"nx ":222,"nul":298,"num":443,"nus":3075,"nut":506,"nty":550,"nto":2015,"ntu":367,"nts":334,"ntr":2166,"nti":3110,"nth":1365,"ntl":140,"nta":3026,"nte":4904,"nsu":730,"nsy":214,"nso":325,"nst":981,"nsf":180,"nse":669,"nsh":461,"nsi":2204,"nsl":567,"nsk":139,"nsc":152,"nsa":421,"nsb":373,"như":5336,"nt ":8221,"ngư":22262,"nqu":229,"ns ":3001,"noc":411,"nod":303,"hĩa":2885,"nob":365,"nol":370,"noi":432,"nop":786,"nom":551,"non":799,"not":862,"nos":776,"nor":939,"now":1063,"nov":236,"nou":281,"nne":5126,"nna":750,"nno":345,"nni":716,"nns":289,"nma":453,"niê":790,"nhâ":2593,"nn ":413,"nla":2159,"nhá":489,"nhà":6343,"nhó":1299,"nly":637,"no ":1110,"hĩ ":710,"nhì":354,"ngâ":223,"nke":271,"nki":377,"ngà":10009,"nka":598,"ngô":1896,"nkt":202,"nja":290,"nii":438,"nig":289,"nif":242,"nie":473,"nid":3745,"nic":2037,"nia":5524,"nk ":242,"nix":164,"niu":181,"niv":273,"nis":1435,"nit":1158,"nio":409,"nim":283,"nin":1178,"nik":149,"nil":357,"ogr":267,"ogu":214,"ogi":228,"ogl":349,"ogo":319,"ogn":1408,"oga":317,"oge":346,"oi ":1139,"ohn":303,"oha":229,"ohe":168,"ogy":195,"ois":1103,"oir":3370,"oit":1455,"oin":300,"oil":149,"oid":1389,"oie":174,"ok ":359,"ol ":657,"oce":820,"och":1882,"oci":330,"ock":741,"ocl":146,"oco":568,"ocr":154,"obu":172,"oe ":211,"oca":1110,"occ":493,"ode":1045,"odi":450,"odo":1089,"odr":210,"oct":1918,"ocy":317,"of ":6954,"oda":691,"dươ":848,"oen":367,"odu":285,"oed":204,"og ":551,"oft":282,"off":252,"ofe":161,"oa ":13629,"oc ":1250,"oan":1921,"oad":230,"oba":818,"od ":1168,"oar":504,"oas":324,"oat":240,"obo":175,"obr":145,"obl":325,"obi":968,"obe":655,"nym":211,"nza":905,"nze":176,"oya":255,"oxy":147,"oxi":202,"oz ":147,"guể":1293,"ows":383,"owl":142,"own":1769,"owi":183,"ozo":255,"oza":724,"otu":288,"oud":174,"oub":187,"ouc":419,"oua":154,"ow ":1038,"oti":1060,"oth":1496,"ote":697,"ott":720,"ots":282,"otr":764,"oto":966,"ost":2982,"osu":324,"ota":1031,"ov ":258,"osi":491,"osh":227,"ose":2073,"osg":493,"osp":425,"oss":826,"osm":547,"oso":413,"osn":140,"oy ":273,"owe":547,"ovi":954,"ovo":159,"ouv":263,"oux":242,"ova":705,"ove":2204,"oug":763,"oui":391,"oul":679,"oun":2537,"oup":387,"ous":2368,"our":3149,"out":2276,"opo":1519,"opp":188,"opi":1120,"opl":220,"ope":1422,"oph":3191,"opa":411,"os ":2470,"opu":314,"opt":1403,"ops":1255,"oon":440,"ool":189,"oom":247,"ook":283,"oog":197,"ood":513,"or ":3376,"oot":347,"oor":232,"ork":631,"orl":473,"orm":2975,"orn":1953,"oro":870,"orp":1047,"orr":2602,"orc":598,"ord":3003,"ore":2045,"orf":1239,"org":708,"ori":3584,"ou ":1707,"osa":1094,"osc":366,"ort":2762,"ors":1266,"oru":667,"ory":1225,"kín":427,"kíc":629,"ot ":1197,"goể":939,"m² ":639,"orb":599,"ora":2404,"oqu":150,"ola":2194,"old":517,"kê ":1566,"giể":12764,"on ":15999,"oli":2444,"oll":1993,"olf":295,"ole":1581,"ols":1043,"olt":149,"olm":148,"olo":2220,"oly":684,"olz":312,"olu":1314,"olv":159,"oka":251,"ghể":2336,"om ":2129,"okk":143,"oki":163,"oke":162,"oku":288,"ona":2358,"ond":2416,"onc":461,"onf":214,"one":2805,"ong":59905,"oni":4577,"onl":675,"onn":2036,"kên":176,"ono":1589,"ons":1629,"ont":3656,"onu":697,"onv":312,"ony":549,"gũ ":341,"kí ":158,"oma":3160,"oo ":152,"ome":1667,"omb":1058,"omi":1212,"omm":2408,"omp":760,"omo":798,"kéo":312,"omu":461,"omy":255,"op ":502,"kì ":200,"la ":10761,"ính":11878,"ín ":1003,"há ":535,"le ":10516,"lca":204,"ít ":628,"lch":163,"lf ":224,"lde":761,"ldb":159,"lda":161,"hào":150,"ldo":198,"hàn":21780,"hàm":435,"hài":213,"ldi":250,"lab":417,"lac":1406,"lad":738,"lae":401,"lah":182,"lag":424,"laj":292,"lai":1546,"lal":167,"lan":10384,"lam":1066,"lap":209,"lao":259,"lar":4422,"lat":2293,"las":1229,"law":585,"lau":512,"lav":645,"lay":1413,"lba":423,"hà ":7105,"ld ":1873,"lbe":635,"lbi":189,"lbo":527,"lbu":797,"gô ":876,"góc":144,"ky ":446,"ích":17834,"cuể":3904,"gôi":662,"góp":269,"gôn":1009,"hìn":3185,"llé":141,"hìm":147,"lpe":2886,"lpi":216,"lph":225,"ls ":3004,"híc":534,"hía":11942,"lok":158,"lon":3179,"lom":1001,"lop":1213,"lor":1602,"lod":250,"loc":750,"loe":167,"log":693,"loi":242,"los":940,"lot":496,"lou":372,"lov":598,"low":793,"hêm":276,"lob":302,"hí ":2215,"liê":1520,"hép":885,"lmo":317,"lme":324,"lma":282,"hì ":1109,"lti":486,"lto":187,"hó ":498,"lud":253,"luc":198,"lue":351,"lso":351,"lst":1066,"lta":363,"lte":462,"lu ":183,"lse":196,"loà":31500,"lsa":619,"ía ":12221,"hín":8169,"lt ":1144,"lhe":150,"lha":193,"hãn":1016,"lge":195,"li ":845,"lga":417,"hât":447,"hâu":5143,"hân":32338,"hâm":245,"lfe":172,"ley":541,"lex":375,"leu":725,"lev":279,"les":4804,"hát":4309,"let":890,"ler":1633,"leo":683,"háo":303,"lep":286,"háp":24791,"hám":208,"lem":456,"len":2814,"hán":13040,"lel":163,"lei":443,"hái":3807,"leg":371,"lef":140,"led":786,"hác":3511,"lec":514,"leb":324,"lea":958,"lls":526,"llu":1871,"lly":728,"lo ":703,"lla":8252,"llb":208,"lle":6069,"lli":4980,"llo":3130,"lks":330,"hê ":529,"diể":17680,"lka":390,"lm ":305,"ll ":2030,"hè ":211,"lit":1006,"lis":1811,"lip":1960,"lio":1480,"lin":3515,"lim":803,"liz":196,"liv":616,"liu":661,"lic":1528,"lid":3931,"lia":3554,"lk ":142,"lik":204,"lii":571,"lig":457,"lie":1623,"lif":1017,"ma ":3578,"húa":466,"húc":1589,"hún":1289,"hút":209,"húy":143,"mb ":269,"ìm ":8521,"mac":644,"mai":885,"maj":203,"mad":498,"mae":190,"ìn ":392,"mag":301,"hür":727,"mar":2810,"mas":488,"mal":1566,"man":6200,"maz":173,"mat":1698,"mba":981,"mbl":196,"mbi":1974,"mbe":1329,"mbr":351,"mbo":504,"me ":3769,"iá ":976,"iße":139,"mbu":270,"ình":20204,"iàn":475,"med":457,"meg":343,"mea":185,"iác":256,"mec":144,"met":1158,"iáp":2001,"mes":1080,"mer":2891,"iám":415,"mem":171,"mel":1053,"iáo":2698,"ián":260,"men":4045,"mei":235,"luy":242,"hòa":4573,"lva":958,"hô ":347,"lve":227,"lvi":160,"lul":235,"lun":153,"lum":1803,"lut":702,"lus":2401,"ly ":5413,"hóa":2227,"hòm":296,"hòn":1026,"lz ":1932,"hôi":152,"hón":422,"hóm":1446,"hôn":8959,"luô":144,"lyp":567,"lym":264,"lyn":185,"hù ":377,"hú ":960,"hùn":400,"hùa":429,"mpi":548,"mph":909,"mpe":699,"mpr":166,"mpo":339,"mpl":212,"mpu":526,"mps":257,"ms ":540,"moc":217,"mod":141,"mon":2835,"mop":418,"mol":919,"mor":1191,"mos":484,"mot":349,"mou":592,"mpa":2137,"mu ":149,"mua":252,"mst":192,"my ":346,"mur":466,"mus":478,"mul":387,"mun":1488,"hăm":190,"hăn":308,"mi ":443,"min":2275,"mil":2845,"mir":352,"mis":870,"mit":1161,"cơ ":2355,"mic":1181,"mib":195,"mia":637,"mie":192,"mid":343,"mo ":242,"ièr":623,"mm ":173,"iêu":3120,"mni":139,"iêm":793,"iên":15316,"mno":232,"mmu":465,"mmi":508,"miê":868,"mmo":992,"mma":550,"mme":1127,"xâm":158,"xây":774,"xã ":6613,"xác":753,"thể":105642,"tiể":16334,"vĩ ":1285,"Để ":4107,"suể":581,"Đểt":393,"Đểu":259,"Đểa":425,"Đểc":8666,"Đểi":2655,"Đển":2345,"Đểo":612,"văn":2376,"soể":246,"vô ":966,"vòn":456,"zue":365,"zur":1019,"ruể":225,"võ ":369,"hưể":6739,"vùn":22597,"vây":180,"vào":6478,"vàn":747,"zen":390,"zel":179,"zer":396,"ze ":541,"vài":326,"và ":39376,"zam":416,"zan":947,"zak":194,"zar":156,"ví ":164,"zon":909,"zo ":189,"vì ":1170,"zna":154,"riể":3937,"zia":217,"zie":194,"zin":147,"zil":497,"yré":2878,"yx ":207,"yth":348,"yst":455,"yso":284,"ysi":882,"yri":846,"yro":276,"yra":354,"yrg":171,"yre":315,"ys ":1775,"yph":446,"ypt":526,"ypr":406,"ypo":300,"ype":314,"yon":322,"uý ":440,"za ":604,"gưể":22834,"uôn":11800,"uôi":272,"quể":14720,"ye ":286,"uá ":683,"yca":261,"yce":225,"ych":303,"ycl":287,"yco":153,"yct":483,"ydr":465,"yer":937,"uán":332,"yen":509,"ya ":1624,"yat":304,"yan":957,"yal":151,"uê ":487,"yla":353,"yle":207,"yli":383,"yll":1078,"ylo":482,"ylv":243,"ylu":187,"yma":185,"sĩ ":1783,"yo ":184,"yme":163,"ymp":602,"ymn":164,"yna":220,"yne":184,"yno":257,"uân":5407,"yi ":308,"tăn":371,"yho":211,"yin":196,"tín":2825,"để ":24120,"tíc":15647,"đểy":569,"xtr":322,"đểu":7023,"đểt":4542,"đểa":6133,"đểi":9089,"đểc":6272,"đển":28910,"đểo":4093,"đểp":378,"đểm":552,"tên":7356,"tìn":624,"tìm":8334,"xon":351,"xoa":253,"tù ":245,"tô ":345,"tòa":324,"xuy":162,"xun":238,"tôn":573,"săn":488,"xi ":160,"tây":9977,"tâm":1507,"tán":178,"xem":772,"tác":2521,"tái":142,"tàn":309,"tàu":1978,"nơi":1970,"phể":19501,"xil":335,"xin":153,"xic":980,"xa ":336,"tài":1059,"xce":150,"xe ":304,"xas":712,"xan":855,"ww ":171,"www":171,"són":349,"sôn":1977,"wo ":144,"yểu":888,"yểt":2656,"yển":27686,"sên":250,"wn ":1674,"sèr":449,"ws ":411,"wor":456,"woo":295,"we ":324,"sân":742,"wes":568,"wer":566,"sáu":219,"sát":605,"wen":170,"sán":1258,"wel":193,"wei":504,"wed":169,"wee":268,"web":356,"sác":1906,"whe":719,"whi":453,"răn":535,"sâu":259,"wi ":419,"wit":1057,"wig":1125,"wid":265,"wic":172,"win":477,"wil":183,"rös":588,"lưu":884,"vuô":11318,"dưể":1608,"rùn":419,"wa ":340,"rúc":638,"wan":646,"wal":651,"way":264,"wat":547,"war":864,"was":494,"wai":552,"rüc":145,"ría":161,"vre":519,"rò ":634,"vua":1478,"vul":314,"rõ ":263,"ròn":162,"rôm":369,"via":1024,"vir":262,"vil":2132,"vin":903,"vig":163,"vic":424,"vid":453,"vie":338,"ngể":4112,"vit":212,"vis":359,"nhể":20937,"ré ":197,"niể":631,"rén":2896,"viê":2261,"rì ":216,"rên":16855,"rí ":838,"voi":343,"vol":291,"von":231,"vor":176,"rìn":2591,"vi ":814,"râu":162,"rãi":238,"ver":2511,"ves":443,"vet":169,"ràn":171,"rào":384,"rái":592,"rán":159,"ven":2308,"vel":746,"rác":292,"ve ":1535,"val":496,"vak":211,"van":1011,"var":683,"vat":444,"rà ":170,"vad":360,"vai":638,"va ":1421,"uyê":4853,"cưể":274,"uze":169,"uzn":158,"uya":181,"uxe":167,"uxo":172,"muể":253,"ux ":1397,"uvi":315,"uve":890,"uy ":4510,"usk":685,"ush":495,"usi":1086,"use":2256,"usc":486,"usa":422,"usu":188,"ust":2067,"uss":2125,"utm":305,"uth":2069,"uti":986,"ute":4039,"uta":488,"utt":513,"uts":241,"utu":168,"uto":356,"us ":12540,"ut ":1468,"urb":527,"ura":1745,"urc":370,"ure":2141,"urg":4458,"uri":3154,"urk":298,"urn":505,"uro":993,"urp":172,"urr":1188,"urs":436,"urt":1515,"uru":494,"ury":261,"ur ":3979,"uph":337,"upi":208,"upe":461,"upl":256,"umi":350,"umo":202,"uma":655,"umb":1047,"ume":427,"unt":1093,"uns":220,"uni":1404,"unn":257,"unc":850,"und":2117,"una":410,"ung":28650,"une":861,"up ":561,"uki":214,"um ":5338,"ulu":810,"ult":827,"ulo":594,"ulm":200,"ull":475,"uli":2981,"ulg":343,"ule":468,"ulc":170,"ula":2994,"ulb":224,"miể":7160,"un ":876,"uid":1911,"uil":817,"uin":1133,"uis":537,"uit":1805,"ul ":704,"ugh":635,"uge":202,"ugl":142,"ui ":422,"uga":249,"ugu":343,"uco":341,"uct":140,"ucu":155,"uda":464,"ude":797,"udi":503,"ubs":175,"ubr":196,"uca":423,"ue ":2123,"uce":268,"ucc":527,"uci":266,"uch":1204,"ucl":244,"uck":465,"uet":161,"uev":189,"uer":585,"ues":940,"uff":186,"udo":607,"udw":163,"uee":563,"ued":1142,"ueb":187,"uen":891,"uel":938,"ub ":179,"ua ":4516,"uay":450,"uat":643,"uar":339,"ual":262,"uan":4521,"ubi":473,"ubl":385,"ube":682,"ubf":310,"uba":515,"ud ":256,"uai":209,"uad":968,"tze":378,"tyl":438,"typ":380,"bưể":9335,"trư":5334,"trù":418,"ty ":2056,"trú":686,"trò":743,"trí":887,"trì":2564,"trê":16809,"trá":625,"trà":444,"tvi":145,"tuy":1965,"tur":1038,"tus":1579,"tut":187,"tui":1819,"tul":991,"tun":226,"tum":525,"tud":242,"tuc":215,"luể":1046,"tz ":904,"two":235,"tră":326,"ts ":2029,"lũn":205,"tre":2316,"loể":3367,"tt ":262,"tra":13075,"thơ":816,"tri":6787,"tru":17464,"tro":55540,"thư":5419,"tu ":263,"try":204,"toá":1052,"tsc":237,"toà":1057,"tsu":330,"tsw":157,"tta":873,"tte":2605,"tti":475,"ttl":380,"tto":705,"ttp":325,"tts":284,"thă":146,"tme":444,"tma":160,"thú":506,"thù":145,"to ":4755,"thô":2398,"tiê":3084,"tp ":325,"tna":209,"toe":205,"tod":450,"toc":558,"toi":213,"tog":204,"tob":196,"tou":1449,"tos":429,"tot":153,"tow":612,"tom":1725,"ton":3013,"tol":487,"tor":2310,"top":602,"tr ":327,"tii":370,"til":3476,"tif":586,"tie":501,"tig":741,"tir":204,"tiq":562,"tit":511,"tis":1648,"tin":5106,"tim":1567,"tip":239,"tio":2405,"thy":410,"thu":53072,"thw":183,"tia":1585,"tic":3507,"tid":1768,"tiu":237,"tiv":602,"tli":260,"thê":286,"thé":143,"thí":558,"thì":784,"liể":1722,"tla":967,"thâ":11890,"thà":11154,"tle":1005,"thá":12170,"tem":2257,"ten":2299,"tep":155,"tei":2098,"tel":2040,"tee":338,"teg":403,"tea":605,"tec":172,"ted":1492,"tfa":159,"th ":4032,"tev":154,"teu":168,"tet":184,"tes":3544,"ter":9430,"ti ":720,"tho":1935,"thm":205,"thr":908,"the":21046,"thi":5961,"tha":4235,"之三 ":187,"之万 ":161,"rưể":6336,"之专 ":252,"ăk ":141,"ăm ":28988,"ăn ":5275,"ăng":3284,"xưa":183,"vươ":541,"nưể":35806,"丘 ":240,"mưể":240,"专 ":1368,"xuể":3053,"並 ":377,"tươ":996,"lưể":2704,"三 ":1277,"丁 ":542,"万 ":771,"uyể":30286,"乙 ":247,"sư ":673,"tư ":1117,"zèr":162,"vũ ":670,"ürt":532,"üri":758,"viể":4820,"rươ":293,"rưn":427,"tuể":1284,"trể":43603,"yêu":353,"之 ":589,"yên":4958,"sơ ":163},"n_words":[13809827,17315344,13396979],"name":"vi"}
\ No newline at end of file
text/langdetect/profiles/zh-cn 0 → 100644
View file @ b309ea1b
{"freq":{"·":11798,"é":695,"и":659,"о":642,"а":705," 《":2860," 。":4044," 、":2042,"あ":2229,"。":93258,"、":80590,"》":12787,"《":12801,"ア":2133,"乱":17692,"书":4419,"习":841,"乡":1808,"九":2519,"也":8266,"乘":28571,"乐":5294,"乌":1217,"义":4779,"之":17358,"久":747,"主":15497,"为":43069,"举":3076,"丽":1041,"丼":1241,"丰":817,"临":983,"个":19411,"中":47239,"两":4794,"严":592,"丛":1367,"业":8072,"东":12690,"丞":9778,"专":3303,"丕":15196,"世":9256,"丈":146015,"三":7927,"上":15305,"下":7962,"不":69712,"与":14330,"一":51232,"丁":117148,"七":1693,"万":2760,"价":1006,"份":14596,"任":5559,"以":21926,"令":1161,"代":10675,"们":2426,"他":7464,"仙":673,"仅":1129,"仍":888,"从":3822,"今":2840,"亲":1398,"人":38353,"亡":667,"产":5405,"亦":2742,"交":20817,"京":3333,"云":2725,"五":3431,"亚":46408,"些":2757,"了":8577,"争":2347,"予":591,"事":19248,"二":6378,"于":42781,"使":59599,"低":1173,"住":1250,"位":13424,"但":4207,"作":14815,"何":21331,"体":8040,"伯":2492,"传":4668,"伦":1894,"伊":2356,"企":1149,"会":16875,"优":845,"休":48239,"众":1421,"信":7840,"俄":2213,"保":3387,"侧":721,"供":2204," 分":744," 公":1819,"商":3626,"哥":1688,"品":4389,"响":1404,"和":23304,"周":2010,"呼":663,"命":2331,"员":7153,"启":817,"含":1431,"吴":771,"名":20347,"同":8476,"后":12165,"吉":2174,"合":7745,"各":3613,"向":3047," 号":1564," 台":812,"域":2609,"城":5315,"培":3476,"基":6619," 名":675,"址":719,"坦":1302,"坡":2693,"土":2149,"圆":692,"场":5846,"地":26817,"在":35727,"圣":2664,"回":1392,"四":5911,"团":4373,"因":6183,"园":2775,"围":1767,"图":2777,"国":50445,"器":3296,"况":701,"冰":646,"决":1729,"冲":743,"农":1200,"军":7136,"写":2568,"册":628,"再":1221,"内":8287,"击":1569," 丕":929," 世":1671," 丈":5741," 不":1283," 一":646," 丁":3946," 万":1431,"兰":5551,"共":7134,"关":4776,"兴":1795,"其":12214,"具":2485,"兹":634,"养":660,"入":4429,"全":7377,"八":1932,"六":2119,"公":17034,"党":2412,"元":4144,"克":7641,"光":2911,"先":2098,"免":623,"停":661,"原":6718,"压":796,"厂":831,"历":4017,"厅":672,"去":1176,"县":5347,"厦":614,"变":2770,"受":2511,"取":2479,"发":12789,"双":1530,"反":2487,"及":17913,"友":732,"又":5333,"参":2872,"司":7147,"号":5641,"台":13293,"可":7699,"只":2126,"口":4422,"化":7453,"包":4823," 何":732,"区":18524,"医":1928," 位":590,"南":15302,"单":3024," 使":1450,"博":1783,"升":971,"千":1226,"十":5342,"协":2640,"华":6868,"半":2037,"卷":760,"印":3243,"即":2844,"卡":3152,"卫":1639,"力":4944," 人":2100,"办":2818,"动":10155,"助":1407,"加":7203,"务":5246,"势":871,"劳":804,"勞":1639," 休":920,"分":15267," 个":2399," 中":1862,"刘":669,"则":3203,"创":4231,"初":2398," 之":647,"别":3560,"利":8681,"到":6365,"制":7035," 乘":758,"前":10878," 乱":770,"剧":3129,"副":860," 亚":733," 天":581," 大":1004,"工":9317,"已":3013,"巴":5253,"州":7529,"川":3028,"山":12651,"属":10137,"展":3788,"屋":1097,"届":1515,"局":2483,"层":1590,"居":1947,"尼":5208,"就":2894,"尚":3502,"少":2443,"小":25275,"将":4225," 多":650,"岸":1431,"岭":590,"岩":988,"岛":4996,"岁":688,"录":1700,"归":696,"当":5254,"形":4076,"役":939,"影":4410,"式":6888,"异":925,"开":7255,"引":4831,"张":2153,"弹":947,"强":1613," 小":894,"念":1709,"往":1560,"律":1732,"得":4936," 家":600,"德":8327,"广":7680,"并":7400,"年":47488,"干":1556,"平":5989,"帝":2672,"帕":667,"师":2671,"希":2317,"布":7549,"常":6171,"席":1225,"带":2534,"延":769,"建":8867,"库":1470,"底":1106,"应":3484,"店":1431,"庙":584,"庆":953,"康":1164,"度":6769,"座":2603,"大":34268,"央":1321,"天":7035,"夫":2315,"太":3274,"头":2350,"失":939,"备":1259,"处":4116,"复":1700,"外":5857,"多":11036,"奥":3388,"女":3642,"好":1250,"奖":2274,"如":3936,"始":3351,"委":2437," 和":850,"增":971,"境":2254,"声":4998," 在":1140,"子":9623,"存":2538,"学":28915,"安":5174,"它":4574,"宁":1619,"定":6314,"实":4032,"宝":999,"宗":2085,"宫":1054,"客":2272,"宣":1095,"宾":780,"家":33525,"富":1265,"密":1755,"察":855,"导":2989,"对":7380,"威":2129,"媒":887," 国":713,"区，一":689,"更":2085,"曲":2749,"曾":3299,"是":61140,"映":608,"春":892,"显":972,"星":4368,"易":1898,"普":2707,"智":818,"晚":728,"架":926,"林":7036,"果":2196,"极":1459,"构":3349,"查":1580,"机":7949,"未":4221,"木":1876,"术":4302,"本":13564,"望":1007,"朝":3840,"期":7068,"朗":953,"月":15728,"有":24992,"服":2639,"最":10271,"松":1118,"杰":812,"杨":679,"来":9550,"条":3385,"村":1739,"李":1577,"杀":947,"杂":1265,"权":2775,"播":2492,"·丁":954,"·丈":771,"摄":716,"料":1677,"文":14966,"施":1293,"斯":13962,"断":823,"旁":959,"旅":1334,"族":3701," 或":968,"时":14785,"无":3416,"旧":1079,"日":21151,"早":2138,"放":2159,"改":3194,"收":1975,"支":2892,"教":9551,"故":1906,"数":7124,"整":1497,"括":3402,"拥":1168,"拉":7109,"拔":3550,"报":2620,"护":1665,"技":2723,"抗":915,"投":1684,"执":1062,"扩":636,"承":1002,"批":885,"所":11521,"手":3277," 年":38848," 平":1187,"打":1400,"户":1297,"房":1033,"戏":2673,"我":858,"成":16718,"或":10994,"战":6655,"提":4221,"推":2158,"控":1211,"接":3776,"排":1222,"换":868,"据":3024,"持":2131,"指":5889,"情":1949,"息":1214,"态":1462,"总":5550,"感":998,"游":3622,"温":1133,"港":10900,"清":2634,"湾":8336,"湖":3858,"源":3031,"满":827,"演":3628,"区，多":1252,"澳":2170,"气":1964,"民":10950,"水":5383,"江":5857,"汉":2630,"求":1033,"汇":1020,"沟":938,"沙":2368,"河":5488,"油":1041,"治":5001,"没":1471,"泽":750,"波":2738,"派":1913,"活":2831,"洲":5289,"测":1385,"济":2241,"流":4509,"消":1003,"深":1422,"横":631," 是":2568," 月":13702,"区，常":666,"武":2208,"此":5466,"止":1051,"正":4102,"死":6678,"歌":2416,"次":4906,"欧":2758,"款":923,"母":1743,"比":4805,"毕":833,"毒":762,"案":1633,"桥":1371,"树":1023,"标":3335,"样":1395,"栽":2997,"根":2240,"核":1380,"校":3605,"楼":1695,"植":5185," 日":10844,"概":864,"石":3358,"知":2149,"省":5247,"着":1639,"皇":2205,"的":145656,"盖":717,"监":811,"盘":598,"目":9318,"直":3003,"白":2529,"百":1846,"登":1073,"病":1344,"町":605,"画":2451,"甸":900,"电":10706,"田":1994,"由":17497,"用":13911,"生":19204,"甘":1358,"略":871,"留":781,"界":6597,"理":9553,"球":6996,"班":1750,"玛":789,"王":5331,"现":8430,"环":2438,"独":1820,"状":1446,"片":2527,"牌":1136,"物":13958,"特":10095,"爱":2167,"照":1002,"然":2677,"热":1483,"点":3443,"火":1816,"灵":903,"缅":631,"缘":1067,"编":2591,"缩":977,"罗":6436,"网":4079,"置":1765,"署":901,"美":10457,"群":2218,"纳":2534,"纽":906,"线":7551,"红":1720,"约":5717,"级":4065,"纪":4115,"结":3008,"统":6645,"绝":650,"络":1469,"给":1157,"细":1259,"织":2183,"组":5795,"经":8789,"终":1135,"维":3625,"综":661,"绿":800,"继":1038,"续":1408,"索":1233,"素":1524,"类":5149,"米":9738,"系":8292,"等":12322,"策":957,"笔":614,"第":11099,"篇":721,"简":4298,"算":1987,"究":2923,"空":3846," 的":2781,"程":4573,"竞":659,"站":6147,"立":9651,"童":907,"突":730,"票":886,"神":3463,"社":4420,"示":1536,"积":2267,"移":1075,"称":17001,"私":738,"科":10282,"离":1553,"福":3324,"确":1094,"础":692,"破":649,"码":1376,"要":8323,"视":4552,"规":2234,"观":2303,"见":2171,"览":667,"角":3015,"解":2300,"西":17559,"被":7905,"街":2230,"行":14959,"表":5479,"认":2753,"计":5438,"训":622,"讯":1488,"议":3045,"让":773,"记":2357,"设":6237,"许":1740,"论":3372,"该":4765,"说":3972,"诸":678,"诺":1644,"读":946,"证":1510,"识":1123,"评":1093,"词":2012,"译":3205,"诗":967,"试":1000,"话":1875,"警":737,"言":2970,"路":9754,"越":2100,"超":1907,"足":2749,"资":4130,"赛":5990,"起":4293,"负":1207,"贝":1346,"财":832,"责":1208,"败":623,"货":901,"质":2689,"购":664,"贵":1643,"费":1407,"象":1888,"调":1492,"谷":1826,"过":6354,"进":5216,"还":1606,"这":6952,"连":2790,"远":1319,"运":6417,"近":3105,"辽":711,"达":4214,"边":2785,"较":2013,"辖":1462,"输":1210,"辑":1374,"车":6585,"轨":655,"转":1925,"轮":727,"软":1659,"轻":756,"载":1404,"身":2869,"脑":1283,"脉":651,"腊":1076,"致":1313,"至":9855,"自":8792,"而":9496,"者":7418,"职":2157,"联":6161," 米":6968,"肃":1126,"股":1262,"育":2953,"胜":1031,"能":5645,"药":977,"荣":690,"草":3994,"获":2004,"莱":1327,"菲":926,"般":2569,"航":2316,"舰":942,"艺":2269,"艾":805,"色":3575,"花":3115,"节":2402,"英":9686,"苏":3117,"著":2998,"营":2531,"萨":1866,"落":1487,"蓝":701,"蒂":676,"虽":721," 英":812,"频":899,"题":1997,"预":942,"领":2926,"食":1377,"飞":1436,"风":2500,"顿":1362,"顺":631,"项":2377,"顶":716,"页":780,"馆":2371,"香":9519,"验":1104,"高":8988," 阿":664,"马":7083,"鲜":1464,"鲁":1516,"鱼":955," 香":692,"黑":1900,"黄":2293,"龙":3881,"造":2929,"选":3181,"送":619,"适":644,"通":7604,"速":2166,"遗":895,"邻":1194,"郡":912,"部":14531,"都":5243,"配":1056,"金":5677,"野":1099,"量":3834,"里":8179,"重":5583,"释":634,"银":1422,"铁":4586,"针":594,"钟":734,"长":12428,"镜":635,"镇":2371,"锡":594,"锦":662,"销":827,"闻":1352,"间":8313,"问":1446,"门":4685,"际":4272,"陆":5534,"陈":1215,"降":626,"限":2379,"陕":1187,"院":5166,"除":1569,"险":710,"队":3990,"阶":1080,"阴":725,"防":1166,"阳":2041,"阿":4439,"随":1152,"难":627,"隶":660,"青":2398,"非":3368,"面":6531,"需":1195,"音":4816,"韩":1018,"가":589,"）":53342,"（":53630,"－":1381,"，":211761,"：":15751,"；":5849," （":2857," ）":2917," ，":8290,"国的特":945,"植物。":2891,"植物，":1199,"基丁教":662,"等地，":3010,"民共和":1261,"。 ":4085,"、 ":2429,"》 ":659,"地区，":3536,"。这":1769,"、陕":800," 、 ":1160,"、福":680,"。现":602,"、甘":833,"。由":929,"、西":1056,"、贵":865,"。该":1506,"四川、":1228,"、广":1717,"、山":2033,"国大陆":3832,"、安":622,"。它":1480,"、四":1328,"。在":1915,"、台":689,"。分":2961,"、印":861,"。其":1173,"、湖":1562,"、河":1285,"、江":1104,"。此":760,"》是":802,"、日":634,"ああ":1707,"、《":1198,"》、":1065,"》中":595,"《丈":900,"、休":601,"。他":1369,"、云":1236,"。乘":742,"、人":909,"。丁":940,"、不":1336,"、丁":2633,"、丈":4209,"、乘":1367,"、中":959,"。丈":1034,"アア":1643,"地区的":687,"》（":2220,"》，":1819,"在中国":1180,"栽培。":2912,"、贵州":848,"是香港":1721,"立于 ":1061,"从 ":609,"人 ":623,"以 ":631,"于 ":10544,"了 ":641,"亚·":946,"亚 ":1478,"休 ":1064,"会 ":652,"使 ":1090,"不、":2097,"不。":742,"丈》":600,"丈、":2959,"丈。":2119,"丁、":2210,"丁。":2121,"一。":1805,"东、":1223,"中、":800,"人。":1182,"事。":826,"亚、":1600,"亚。":687,"交。":780,"丈山":758,"丈属":948,"不家":1629,"之后":1285,"丈小":1097,"丈家":1182,"丁属":1251,"中国":13581,"丈子":859,"丈学":961,"一家":830,"乱丈":1142,"为台":739,"丈大":637,"举办":651,"丁大":616,"何。":612,"乘丁":814,"乘一":737,"乘丈":920,"中华":3016,"乘丛":864,"丈地":713,"之一":4710,"丁国":1036,"丁地":630,"东南":852,"主义":1789,"为主":1114,"为中":1501,"为丈":1939,"为一":949,"为丁":953,"丈和":636,"为了":902,"不同":2049,"中使":2667,"不区":1235,"中一":647,"不军":620,"个人":1067,"丈克":1016,"丈其":691,"不公":924,"两个":961,"不使":1931,"休。":1293,"休、":1110,"丁克":614,"东不":1592,"丛中":711,"丁军":992,"丁兰":618,"不交":3736,"不京":1465,"不事":949,"丈休":1776,"丈使":1087,"不休":658,"丕丈":949,"丈不":1018,"丈丈":10643,"丈丕":925,"丈丞":767,"丈中":605,"丁休":2172,"丈为":629,"丈之":694,"上不":1488,"一位":1048,"丈乘":1009,"丈乱":1342,"丁作":779,"丈事":642,"丁使":3178,"丈交":632,"不丈":1417,"不丁":1361,"丈亚":1470,"不不":1140,"与丈":673,"一丈":695,"丁丈":5202,"丁丁":3673,"丁不":1113,"一个":9742,"丁乘":875,"一亚":4760,"一些":1051,"丁乱":789,"丁亚":2029,"份、":719,"丈一":1128,"丈丁":6021,"主教":1120,"任何":656,"于山":605,"交大":1013,"企业":965,"为是":626,"中文":1113,"人口":1818,"一次":948,"丈林":809,"他们":991,"产品":768,"事场":701,"以丈":590,"人使":892,"丁是":769,"丈是":785,"一条":1013,"不拔":3372,"二十":706,"人乘":690,"云南":1737,"人丁":945,"人丈":706,"主席":689,"丁教":806,"于台":1035,"元 ":583,"丁斯":907,"丁文":660,"一所":719,"亚使":601,"交休":767,"事务":628,"乘大":1199,"亚丈":1056,"不式":1110,"亚丁":910,"中学":1267,"亚亚":814,"交不":722,"使。":1718,"使、":1407,"丁店":632,"一座":888,"中央":1281,"于丁":1020,"于不":3550,"于丈":1169,"事交":1241,"于中":1731,"中的":2873,"休如":834,"丈科":1509,"亚栽":2911,"东省":644,"份年":663,"使休":784,"使代":599,"使中":607,"二次":594,"使丈":1433,"使上":903,"使丁":935,"下的":912,"世界":3851,"上的":1685,"何丁":623,"丈的":3617,"于日":763,"乘江":1087,"位于":6910,"丁的":3074,"不生":996,"作为":1517,"不的":1824,"也有":715,"不现":1191,"份围":818,"人工":3099,"丈球":620,"休丈":1574,"休丁":1348,"以及":5720,"不治":1654,"也是":2441,"休休":1177,"休使":948,"交的":754,"何成":650,"但是":741,"人的":1301,"事的":883,"人物":960,"丁西":582,"产生":952,"亚的":1008,"一般":2436,"人民":2356,"丈至":636,"丈草":591,"使团":1466,"前 ":886,"作家":983,"作品":1438,"亚洲":979,"使兰":933,"世纪":2136,"乘的":934,"到 ":1169,"丈 ":2639,"丈·":660,"丁 ":1901,"丁·":957,"为 ":5249,"地、":838,"国、":813,"又译":658,"发行":1130,"可能":964,"南部":1207,"名称":1365,"后的":584,"名的":1485,"同的":919,"商业":792,"使（":777,"使，":2980,"又称":2280,"台湾":6649,"位，":691,"发现":998,"体，":607,"何，":1182,"作，":878,"发生":1318,"后来":990,"只有":591,"南等":606,"休（":899,"休，":2609,"和国":2085,"会，":853,"会（":981,"同时":1360,"在 ":4342,"命名":845,"份，":752,"国 ":738,"区的":1567,"和丈":1029,"和丁":641,"前身":709,"员会":1240,"交，":1266,"制造":737,"反应":687,"人，":2362,"化的":604,"事，":1473,"亚，":1453,"亚（":751,"亚：":3961,"华民":1238,"发展":2345,"多生长":627,"国的":3079,"国王":741,"城事":1744,"因此":1473,"国民":1000,"基丁":1219,"分，":694,"四川":1896,"地区":6955,"国大":4205,"在台":652," 公里":1220,"国家":4191,"在不":766,"在丈":1143,"在丁":899,"地不":1517,"在中":1500,"内，":588,"国国":1280,"因为":1284,"团体":692,"国丁":732,"国丈":695,"国不":1345,"国人":990,"培。":2913,"公园":1063,"全国":1074,"共和":2100,"共同":711,"军事":699,"公司":6085,"和 ":1051,"克斯":708,"分丁":674,"分为":837," 丈丈":703,"及 ":757,"内信":885,"其他":1807,"内丁":823,"公共":779,"其中":1933,"俄罗":1205,"交通":1010,"代表":1920,"使用":3270,"使理":2624,"使的":2300,"何的":1007,"之间":1601,"作用":691,"何用":717,"传统":899,"作的":824,"何能":734,"九龙":820,"于香":923,"会议":766,"人闻":930,"体育":809,"使究":2862,"不部":1509,"代的":607,"人类":940,"使本":654,"丁近":677,"举行":1293,"主要":4270,"于美":614,"一部":1591,"丈车":720,"他的":941,"专辑":636,"信息":699,"保护":898,"亚言":1720,"休画":658,"休的":1686,"会的":752,"不面":1014,"及丈":729,"及中":2186,"下，":946,"上，":1461,"丈（":2586,"丈，":5165,"参与":744,"半岛":715,"不，":1460,"一，":2377,"丁）":1039,"丁，":4237,"丁（":1706,"包括":3325,"参加":688,"动画":653,"中，":3371,"及其":661,"业，":586,"原名":724,"动物":1359,"名为":1425,"乘，":704,"各亚":724,"又名":874,"印度":2180,"可以":2687,"台不":1436,"乱，":730,"名使":755,"合作":595,"包含":732,"单位":907,"员。":605,"华人":1471,"协会":1039,"南不":934,"公路":1194,"区域":737," 世纪":1447,"化学":839,"分类":693,"利用":693,"医学":647,"历使":2363,"创立":811,"公里":2086,"前尚":2725,"内的":698,"关系":1044,"名。":910,"创作":725,"分别":959,"利亚":1729,"共有":696,"制作":1175,"创办":644,"具有":1055,"区、":855,"区。":806," 中国":719,"南、":2847,"分子":582,"分布":3839,"全球":752,"加乘":908,"州事":599,"工业":864,"工作":1348,"实际":605,"巴乘":819,"属的":3366,"学院":1919,"度、":646,"帝国":1098,"工引":2908,"平不":1296,"山谷":602,"并丁":847,"年代":1820,"广东":1877,"广乘":652,"布在":1655,"山西":700,"小都":652,"布于":1877,"建、":593,"巴使":874,"小说":1496,"、陕西":793,"场，":659,"尚未":2839,"定的":781,"州、":1204,"地，":4149,"川、":1254,"它的":633,"山坡":1678,"学的":914,"国，":704,"学生":932,"小的":1375,"德·":778,"就是":947,"家的":1013,"应用":955," 年 ":13492,"形式":842,"形成":784,"德国":1532,"或 ":819,"影响":1080,"德亚":680,"希腊":1007,"年的":1358,"广西":1228,"建立":1106,"当时":1404,"年至":809,"拔 ":3155,"外，":1036,"广场":674,"广州":765,"建于":690,"建丁":1787,"年在":775,"处，":614,"开始":2055,"工程":1106,"已经":808,"常生":724,"引亚":2921,"广播":596,"开发":1428,"大学":4751,"名：":4034,"后，":2099,"名，":804,"大战":639,"号，":798,"司，":904,"司（":706,"太平":714,"员，":1310,"委员":1628,"多生":1267,"处理":904,"国立":626,"动，":770,"基本":664,"境内":659,"声任":875,"区，":4940,"基础":690,"国际":3114,"大利":1318,"大使":1012,"家 ":943,"天休":592,"天主":779,"大丈":869,"学使":616,"大陆":4400,"它们":581,"安丁":901,"学名":3799,"定义":596,"存在":833,"岛、":590,"家亚":645,"家丈":713,"家丁":849,"学家":1872,"对于":704,"年 ":13993,"小丈":990,"家国":1673,"尼亚":1342,"学校":1549,"它是":712,"家律":640,"属于":2022,"宗教":606,"山东":748,"大的":1819,"品，":659,"未由人":2713,"学、":1095,"媒体":593,"家、":1079,"家。":1319,"学中":593,"大部":622,"是由":1948,"最大":1527,"成，":1007,"最早":864,"是美":1276,"日至":621,"林中":937,"林下":866,"林丈":747,"是日":749,"最丈":683,"教育":1765,"斯特":879,"是指":1893,"最后":916,"服务":2010,"时的":619," 日 ":1067,"有一":1032,"有丈":634,"有关":606,"栽培":2968,"曾经":583," 月 ":10460,"期的":814,"未由":2714,"有的":742,"来的":817,"是香":1732," 年，":2603," 年）":2400,"机构":1217,"有植":939,"有时":593,"时间":1469,"标何":1254,"故事":840,"教丁":619,"教会":604,"教休":765,"文使":804,"、湖不":767,"斯丁":803,"文化":2111,"、江西":640,"式，":710,"是台":693,"是在":1454,"早期":592,"时期":1763,"日本":5547,"数学":761,"、湖南":720,"名：）":3257,"时代":1179,"斯坦":867,"文学":1074,"数据":868,"是位":626,"是以":583,"是中":2851,"日在":675,"是丁":1437,"是一":8458,"是不":724,"是丈":2026,"是 ":2352,"推不":777," 年的":914,"或称":642,"成立":2637,"技术":1644,"成的":1249,"日 ":1181,"斯·":1031,"所有":1061,"拉丁":1110,"委员会":1211,"投资":588,"月 ":10522,"有 ":2350,"年（":1135,"年）":2514,"年，":3020," 年至":781,"提不":749,"提供":1571,"控制":687,"或者":862,"拥有":1075,"家（":883,"家，":2992,"学（":696,"学，":1273,"子，":932,"成。":674,"年间":605," 年在":695," 年代":1447," 平不":1027,"所以":844,"成员":1194,"属（":1286,"成为":2403,"战争":1282,"成何":673,"车站，":720,"总统":750,"小，":1060,"流行":630," 日）":775," 日，":1367,"没有":1287,"活动":1238,"比赛":1111,"江苏":807,"江西":972,"湖不":1117,"湖南":1294,"源于":655,"游戏":1924,"江、":1010,"斯（":605,"文：":2387,"毕业":667,"时，":1279,"死关":792,"日，":1548,"日）":813," 日至":616,"、广西":861,"民国":1569,"民主":899,"欧洲":1589,"民共":1266,"正式":1275,"河南":853,"月，":734,"民族":1066,"期，":613,"河不":810,"称为 ":1204,"根据":1261,"来自":905,"朝鲜":1221,"最高":965,"期间":1013,"有限":1519,"植物":4924," 是一":701,"概念":628," 日在":655,"社会":2250,"的西":629,"的重":753,"第 ":1806,"的第":1619,"物，":2113,"目的":1041,"的是":1254,"的最":739,"的植":2910,"称 ":1447,"积 ":789,"生长":4500,"直接":612,"的特":1539,"的电":996,"的小":1525,"的家":638,"电脑":1011,"的大":1230,"的国":1201,"的基":581,"的地":4246,"电视":2674,"目前":4402,"的丁":3401,"的一":9462,"用的":1236,"生的":842,"球队":888,"生物":1143,"甘肃":1053,"的名":795,"的发":604,"的休":1722,"的使":1923,"的何":678,"的作":618,"的主":1363,"的中":1197,"的丈":5079,"的不":2462,"的乱":628,"的乘":866,"的人":1919,"的交":1075,"的亚":598,"的份":596,"用来":773,"电影":2044,"理论":1071,"生活":843,"生在":746,"电子":1067,"的。":902,"的《":764,"由人":3013,"由于":1683,"用于":1226,"生于":2477,"生产":971,"理学":1070,"王朝":657,"独立":1054,"现在":1080,"环境":892,"的 ":3036,"用。":732,"现代":899,"班丁":801,"物理":701,"特有":1087,"由 ":647,"特别":1034,"澳门":921,"、福建":587,"物。":3636,"而成":666,"网络":1319,"等，":840,"。由于":637,"结构":811,"称，":606,"统治":615,"美国":6262,"有限公":1342,"经济":1788,"线的":727,"统的":590,"群岛":661,"罗斯":1403,"组织":2012,"联休":1568,"联合":1420,"经营":801,"美洲":847,"站，":1417,"站（":605,"立，":948,"约丈":612,"系统":2897,"、甘肃":804,"结丁":584,"纪念":701,"缩写":612,"至 ":5691,"肃、":800,"自 ":728,"组成":1458,"米的":3087,"米至":2745,"空间":581,"简称":3399,"目，":621,"系使":1617,"等地":3350,"的，":1232,"算机":592,"约 ":1747,"天主教":743,"立的":1250,"立于":1279,"生，":616,"用，":772,"科技":622,"第三":1132,"第一":3441,"第二":2122,"科丈":1055,"等。":1256,"科学":1716,"福建":1133,"称为":4237,"站。":627,"角色":608,"认为":1515,"西部":624,"计份":1242,"译为":652,"西班":773,"要的":1104,"视台":583,"被称":1048,"设计":1764,"越南":953,"贵州":1074,"计算":1077,"设立":673,"赛事":631,"过 ":590,"达 ":635,"许多":1084,"这亚":795,"这些":921,"这个":1485,"运动":2493,"选举":733,"超过":649,"软交":1060,"路线":871,"负责":846,"资讯":628,"足球":1709,"行，":1162,"资料":726,"都是":704,"说，":693,"进行":2271,"华民国":1215,"过程":791,"部分":2341,"部份":779,"车站":2410,"通常":1655,"连接":661,"系，":584,"英亚":2018,"自治":726,"自然":791,"英国":2374,"艺术":1217,"自由":876,"般生":684,"航空":1141,"草地":757," 米的":3008,"罗马":1148,"自丁":786," 米至":2742,"米，":928,"联赛":872,"者，":759,"节目":923,"英文":2834,"苏联":584,"获得":1131,"线，":677,"著名":1735,"是台湾":602,"虽然":581,"行。":771,"规份":679,"西南":748,"行的":1255,"西份":1008,"西亚":1199,"西不":1211,"行为":642,"行不":2204,"西、":2735,"中，目":813,"马来":712,"香港":8632,"高丁":607,"间，":1121,"队，":590,"高速":865," 香港":632,"及中国":2044,"公里，":1108,"是一个":2236,"是一亚":2252,"是位于":587,"丈（学":778,"是中国":2142,"部的":1067,"通过":1270,"赛，":689,"长 ":666,"路，":847,"重要":1745,"的第一":601,"铁家":726,"重要的":693,"长于":3283,"长在":1116,"部，":1121,"除了":587,"限公":1343,"阿亚":611,"间的":1117,"阿拉":760,"铁路":1902,"银行":879,"陆的":3096,"里，":1518,"陕西":1134,"音乐":1761,"面积":1528,"问题":913,"非洲":689,"领域":706,"需要":625,"项目":737,"有植物":938,"的特有":970,"华人民":1156,"是美国":1183,"生长在":1097,"的植物":2905,"生长于":3254,"日至 ":606,"前尚未":2719,"最大的":950,"加乘大":716,"是日本":698,"目前尚":2723,"的地区":3123,"甘肃、":797,"的一部":774,"的主要":669,"年），":737,"的一亚":1477,"的一个":3092,"限公司":1342,"年（ ":710,"长于不":2913," ）是":697," ，是":1072,"南等地":586,"），":14139,"（）":3758,"（，":1176,"，）":1561,"：，":733,"：）":4083,"由人工":2914,"，有":1486,"，最":1122,"，曾":1063,"，是":13170,"）是":10848,"，此":660,"，总":746,"，当":886,"，并":4017,"，常":1051,"，故":644,"，指":584,"，所":997,"，或":1328,"，成":1293,"）的":2201,"，目":3648,"，第":777,"，简":2029,"，现":1341,"，由":3911,"，用":638,"，生":3542,"，西":833,"，被":862,"，该":1018,"，经":598,"，美":598,"，而":3223,"，英":974,"（英":2411,"，香":721,"，这":1581,"，通":884,"，《":690,"）。":3713,"）、":2880,"（丁":582,"（学":3658,"，它":1417,"，属":841,"，小":789,"，因":2416,"，在":4524,"，多":1573,"，大":803,"，如":965,"，前":662,"，分":865,"，南":723,"，即":1029,"，包":1287,"）和":952,"，后":1255,"，同":895,"，台":750,"，可":1101,"，又":2947,"，原":1270,"，与":1258,"，不":2776,"，东":861,"，中":1697,"，主":1658,"，为":3616,"（今":666,"，乘":1464,"，也":3256,"，乱":593,"（丈":745,"）为":2108,"，丈":5138,"，丁":4254,"，一":2351,"，休":1379,"，但":3353,"，位":2756,"，使":1942,"，交":917,"，亦":1195,"，于":2786,"，人":883,"，以":3498,"，他":1341,"，从":880,"，份":844,"，共":756,"，其":3552,"，全":1258,"（ ":4029,"） ":1194,"， ":8207,"－ ":821,"： ":1177,"于台湾":746,"云南、":1087,"丁属（":793,"中国的":1325,"中国大":3854,"之一，":2267,"不拔 ":3152,"于不拔":2931,"于中国":1363,"丈属的":710,"人工引":2908," ），":840,"乘江、":593,"特有植":935,"位于香":588,"于日本":718,"交大利":915,"以及中":2006,"一般生":684,"英文：":1509,"亚栽培":2910,"陕西、":802,"人民共":1261,"广西、":800,"：）为":1432,"：）是":1905,"），又":980,"），是":2411,"（）是":1113,"，），":1007,"著名的":779,"（），":1527,"年至 ":713,"面积 ":773,"于香港":916,"之间的":629,"内丁使":615,"成立于":917,"英亚：":1340,"俄罗斯":1205,"，香港":708,"物。分":2814,"公司（":690,"公司，":865,"行不区":1022,"共和国":1949,"分布于":1823,"分布在":1639,"》、《":946,"）是丈":621,"）是一":2670,"，是一":2180,"，是中":1286,"湖南、":689,"あああ":1321,"尚未由":2713,"地，生":2896,"，并丁":652,"，常生":669,"，所以":699,"，又称":1386,"，台湾":584,"，因此":1152,"，多生":1256,"（学名":3651,"。分布":2922,"、印度":793,"、乘江":625,"、云南":1182,"被称为":866,"、山坡":669,"、广东":743,"、四川":1251,"大陆的":3080,"アアア":1275,"学名：":3527,"（英文":1335,"（英亚":1020,"，目前":3438,"，生长":2942,"西班丁":773,"，简称":1929,"工引亚":2908,"平不公":791,"贵州、":836,"广东、":761,"引亚栽":2908,"，包括":1127,"米的地":2908,"，又名":585,"，在 ":658,"，其中":943,"，以及":1003,"，也是":1477,"，位于":2555,"，一般":1217,"，主要":1207,"，为中":658,"，中国":911,"属的植":2824,"，于 ":2118,"丁使、":641,"丈丈丁":631,"计算机":592,"江西、":618,"湖不、":763,"不同的":722,"米至 ":2743,"之一。":1753,"中华民":1237,"中华人":1156,"为中国":948,"不公里":767,"丈丈，":642},"n_words":[4792118,1709982,314544],"name":"zh-cn"}
\ No newline at end of file
text/langdetect/profiles/zh-tw 0 → 100644
View file @ b309ea1b
{"freq":{"·":11773,"é":695,"區，常":664,"и":659,"о":642,"а":705," 《":2780," 。":1867," 、":1053,"あ":2229,"。":93215,"、":80530,"》":12775,"《":12789,"」":16776,"「":16978,"ア":2133,"九":2518,"也":8240,"乘":27365,"之":17356,"久":750,"主":15490,"丼":1230,"中":47219,"並":6623,"丞":85837,"丕":96789,"世":9230,"丈":143774,"三":7943,"上":15307,"下":7965,"不":69580,"一":51222,"丁":112603,"七":1691,"份":8990,"任":5556,"以":21889,"令":1163,"代":10588,"他":7458,"仙":669,"仍":884,"今":2840,"人":38053,"亡":666,"亦":2741,"交":18627,"京":3334,"五":3430,"些":2759,"亞":10406,"了":8549,"予":591,"事":19252,"二":6375,"使":59515,"低":1174,"住":1250,"位":13512,"但":4206,"作":14816,"何":16276,"佐":33991,"伯":2485,"伊":2316,"企":1149,"休":48236,"信":7776,"俄":2093,"係":1210,"保":3393,"來":9528,"供":2206," 分":709,"單":3071,"問":1448," 公":2117,"商":3624,"員":7098,"哥":1699,"品":4392,"和":23261,"周":1446,"呼":664,"命":2330,"含":1432,"名":20323,"同":8443,"吉":2089,"合":7724," 倫":1516,"各":3613,"向":3031,"域":2612,"城":5349,"執":1078,"培":3458,"基":6608," 名":633,"址":721,"坦":1100,"坡":2688,"團":4364,"土":2148,"園":2775,"圖":2763,"國":50470,"地":26714,"在":35708,"回":1107,"四":5909,"因":6124,"嚴":592," 勞":1513,"器":3287,"冰":646,"再":1221," 丞":2854," 丕":3070," 世":1592," 丈":4439," 不":917," 丁":3186,"優":845,"共":7054,"其":12215,"具":2485,"入":4421,"內":8167,"兩":4796,"全":7445,"八":1932,"六":2118,"公":17482,"兒":1569,"元":4231,"克":7487,"光":2846,"先":2097,"免":625,"傳":4645,"價":1006,"倫":51626,"個":19430,"們":2429,"停":661,"原":6791,"去":1179,"受":2509,"取":2465,"反":2477,"及":17959,"友":732,"又":5332,"參":2854,"司":7145,"台":11564,"可":7754,"只":1856," 個":2397,"口":4174,"化":7454,"包":4825," 佐":611," 位":594,"南":15370,"協":2646," 使":1198,"博":1769,"升":830,"千":1228,"十":5341,"區":18522,"半":2039,"卷":655,"印":3241,"即":2842,"卡":3151,"劃":2056,"劇":3028,"力":4955," 人":1795,"助":1406,"加":7145,"勞":44204,"務":5038,"動":10173," 休":691,"分":15261," 中":1418,"初":2396,"別":3548,"利":8617,"到":6362,"制":3819," 乘":601,"則":3204,"前":10854,"副":861,"創":4236," 大":752,"工":9304,"已":3034,"巴":5247,"州":7520,"川":3027,"山":12644,"屬":10111,"展":3787,"屋":1099,"局":2380,"居":1946,"尼":4905,"就":2895,"尚":3522,"少":2442,"對":12131,"小":25320,"導":2988,"專":3315,"將":4225,"島":4996," 多":609,"岸":1457,"岩":955,"彈":1036,"形":4081,"役":939,"影":4543,"式":7142,"引":4806,"張":2155,"強":1613," 小":712,"念":1686,"往":1561,"律":1728,"後":11603,"得":4825,"從":3819,"德":8443,"幹":610,"年":47473,"平":5943,"帝":2671,"帕":627,"希":2358,"布":6774,"常":6175,"帶":2450,"師":2700,"席":1237,"延":769,"建":8865,"廣":7680,"廠":829,"底":1070,"店":1431,"康":1164,"度":6845,"座":2605,"大":34205,"央":1335,"天":6785,"夫":2310,"太":3614,"失":939,"外":5866,"多":11013,"奧":3348,"女":3636,"好":1255,"如":3939,"始":3424,"委":2437,"場":5840,"報":2620," 和":619,"增":971,"境":2254," 在":1006,"子":9582,"存":2418,"學":28894,"安":5183,"它":4320,"定":6314,"宗":2121,"宮":11665,"客":2255,"宣":1095,"家":33259,"富":1263,"密":1751,"察":902,"寫":2568,"實":4042,"威":2163,"媒":887,"更":2088,"曲":2693,"曾":3297,"書":4421,"是":61135,"映":606,"春":891,"星":4383,"易":1898,"普":2726,"智":821,"時":14789,"晚":728,"架":926,"林":7015,"果":2193,"查":1544,"未":4199,"木":1871,"本":13516,"望":1009,"朝":3760,"期":7068,"朗":950,"月":15722,"有":25006,"服":2638,"最":10258,"會":16872,"松":993,"東":12692,"村":1739,"李":1578,"播":2488,"擊":1563,"據":2801,"·丁":953,"·丕":684,"·丈":742,"料":1908,"文":14926,"於":85512,"施":1293,"斯":13761,"旁":958,"旅":1333,"族":3698," 或":592,"日":21067,"早":2137,"放":2161,"改":3194,"收":1971,"支":2879,"教":9547,"故":1906,"數":7013,"整":1506,"括":3403,"拉":7094,"拔":3534,"技":2726,"抗":915,"投":1689,"承":1001,"批":886,"所":11497,"手":3280," 年":38814," 平":1137,"打":1356,"戰":6668,"戲":2673,"房":1031,"我":858,"成":16686,"或":10999,"提":4217,"推":2160,"控":1213,"接":3506,"排":1256,"持":2131,"指":5892,"情":1951,"息":1210,"應":3488,"感":1000,"愛":2219,"游":601,"測":1417,"港":10903,"清":2633,"湖":3859,"源":2955,"滿":823,"漢":2629,"演":3758,"澳":2170,"濟":2246,"民":10942,"水":5379,"氣":1960,"江":5858,"求":1019,"決":1728,"沒":1469,"沙":2360,"河":5480,"油":1041,"治":5045,"波":2725,"派":1934,"活":2827,"洲":5278,"流":4541,"消":1003,"深":1422,"機":7988,"樓":1698,"標":3283,"樂":5292," 是":2270," 月":13683,"武":2208,"此":5462,"止":1051,"正":4102,"歷":3537,"歲":679,"死":6673,"歌":2412,"歐":2776,"次":4908,"款":922,"權":2775,"母":1810,"比":4792,"毒":761,"殺":3118,"案":1653,"栽":2979,"根":2237,"核":1380,"校":3603,"條":3385,"楊":679,"業":8348,"植":5169,"構":3354," 日":10789,"概":795,"石":3331,"知":2143,"省":5241,"眾":1402,"皇":2166,"的":145617,"目":9288,"直":3002,"發":12643,"白":2538,"百":1845,"登":1101,"病":1342,"町":605,"甸":897,"田":1992,"由":17477,"用":13939,"產":5389,"生":19162,"甘":1400,"當":5199,"畫":2821,"略":871,"留":781,"界":6587,"環":2430,"理":9565,"球":7020,"區，一":683,"現":8423,"班":1762,"王":5328,"獎":2259,"獲":1989,"片":2524,"牌":1136,"物":13950,"特":9797,"爭":2331,"爾":10487,"營":2531,"照":1001,"然":2724,"無":3430,"灣":8336,"火":1815,"置":1766,"署":979,"羅":6361,"美":10443,"群":2244,"義":5695,"習":841,"總":5592,"縣":5350,"繼":1038,"續":1407,"索":1368,"素":1525,"納":2465,"約":5697,"紀":4111,"級":4056,"統":6648,"組":5814,"結":3076,"綠":801,"維":3676,"網":4429,"經":8789,"綜":642,"編":2471,"線":7038,"簡":4320,"米":9228,"系":6773,"等":12258,"策":935,"第":11129,"篇":721,"節":2370,"算":1983,"積":2283,"究":2927,"空":4143," 的":1486,"程":4595,"稱":17006,"種":13270,"站":6147,"立":9659,"競":659,"童":907,"突":731,"票":889,"神":3459,"區，多":1245,"社":4421,"示":1588,"移":1020,"私":736,"科":10232,"福":3334,"破":649,"要":8322,"規":2224,"視":4488,"親":1395,"觀":2300,"角":3003,"解":2370,"西":17796,"被":7902,"製":3213," 萬":1397,"衛":1641,"街":2230,"術":4294,"行":14995,"表":5436,"變":2770,"譯":3201,"警":737,"議":3043,"護":1664,"證":1490,"調":1479,"說":3940,"語":12000,"認":2740,"論":3370," 號":1554,"設":6262,"記":2497,"計":5475,"訊":1564,"言":2973,"該":4761,"話":1875,"評":1093,"路":11367,"越":2102,"超":1905,"足":2739,"起":4291,"賓":786,"資":4396,"賽":6003,"質":2688,"費":1408,"貨":906,"責":1207,"象":1864,"谷":1752,"近":3107,"辦":2818,"農":1197,"轉":1925,"較":2015,"載":1405,"車":6562,"身":2869,"致":1208,"至":9837,"自":8751,"而":9484,"者":7426,"聞":13745,"聖":2663," 米":6617,"聯":14082,"聲":1069,"肅":1122,"股":1263,"育":2954,"能":5599,"草":3974,"菲":888,"華":6888,"般":2564,"航":2033,"興":1795,"舉":3075,"與":14328,"艦":940,"艾":758,"色":3577,"花":3113,"英":9681,"藝":2269,"藥":973,"葉":1953,"著":4637,"萬":2757,"落":1486,"蒂":673,"處":4121,"號":5640,"蘭":5557,"蘇":3088," 英":759,"風":2494,"食":1389,"飛":1667,"領":2927,"預":955,"項":2370,"類":5147,"馬":6983,"香":9518,"館":2367,"體":9444,"高":8889," 阿":586," 香":621,"點":3460,"黑":1831,"黃":2289,"黨":2390,"龍":3877,"連":2837,"造":2926,"進":5235,"送":620,"這":6954,"通":7591,"速":2179,"遺":895,"選":3181,"過":6349,"運":6466,"遊":3024,"達":4169,"還":1604,"邊":2782,"郡":912,"部":14529,"都":5256,"配":1052,"醫":1928,"金":5699,"野":1096,"量":3732,"里":6615,"重":5591,"銀":1423,"錄":1696,"鎮":2372,"鐵":4592,"間":8271,"開":7281,"門":4672,"降":626,"限":2369,"院":5168,"除":1568,"陳":1215,"陸":5523,"陽":2042,"防":1167,"阿":4360,"離":1505,"難":627,"電":10735,"雲":2700,"隊":3986,"際":4571,"青":2396,"非":3371,"面":6432,"需":1196,"響":1404,"音":4823,"가":589,"）":53309,"（":53597,"－":1381,"，":211682,"：":15729,"；":5850," （":1546," ）":2103," ，":4859,"車站，":720,"國的特":944,"植物。":2875,"植物，":1199,"基丁教":662,"等地，":2994,"民共和":1261,"。 ":3480,"、 ":1427,"」 ":591,"》 ":624,"國大陸":3816,"地區，":3519,"。這":1771,"、雲":1235,"」的":1264,"、福":680,"。現":601,"、甘":835,"。由":929,"、西":1055,"。該":1503,"四川、":1228,"、廣":1717,"、山":2030,"、安":622,"。它":1379,"、四":1327,"。在":1916,"、台":622,"。分":2945,"、勞":792,"、印":867,"、倫":1945,"。其":1173,"、湖":1562,"、河":1284,"、江":1104,"。此":759,"》是":802,"、日":634,"ああ":1707,"、《":1196,"、「":974,"》、":1063,"」、":966,"」。":2150,"》中":594,"「丕":727,"「丞":592,"《丈":880,"、休":613,"。他":1366,"「丈":1131,"《丕":588,"。乘":718,"、人":863,"、丞":3044,"。丁":930,"、丕":3444,"、不":1334,"、丁":2563,"、丈":4244,"、乘":1329,"。丞":586,"。丕":1165,"、中":959,"。丈":1017,"アア":1643,"地區的":687,"」（":1271,"」，":3388,"」）":800,"》（":2216,"》，":1818,"在中國":1179,"立於 ":1061,"栽培。":2896,"是香港":1720,"休 ":665,"使 ":756,"不、":2094,"不。":739,"丈」":981,"丈》":585,"丈、":2906,"丈。":2027,"丁、":2136,"丁。":1921,"一。":1804,"丞、":1947,"丞。":1850,"丕」":693,"丕。":1789,"丕、":2245,"中、":800,"人。":1182,"事。":826,"交。":660,"亞、":852,"倫 ":745,"丈山":729,"丈屬":937,"不家":1629,"丈小":1088,"丈家":1181,"丁屬":1243,"中國":13565,"丈學":945,"丈子":859,"一家":831,"丕大":655,"乘倫":1335,"丈大":605,"丕地":870,"丁大":588,"乘丁":705,"乘一":736,"佐。":1221,"乘丈":663,"佐、":761,"丈地":748,"丞和":584,"之一":4708,"丁國":1032,"丞勞":850,"丕勞":1045,"丈和":615,"不同":2051,"不勞":723,"中使":2667,"不區":1235,"中一":646,"丞使":1157,"丞倫":1278,"丈勞":1514,"丞人":604,"丈克":1050,"丈其":690,"丕使":877,"一勞":758,"丞佐":1297,"不公":954,"丁勞":1850,"並丁":839,"丕倫":1815,"丞休":1067,"丈倫":1781,"不使":1931,"休。":1287,"休、":1097,"丁克":614,"丞丈":3784,"丞不":839,"丞丁":2627,"丞丕":3712,"丕休":1238,"丞丞":2873,"丕佐":865,"不交":3733,"不京":1465,"不事":953,"丈休":1744,"一個":9748,"丈使":1114,"丈佐":1124,"丁倫":2045,"丕丞":2819,"丕丕":4439,"不休":656,"丕不":779,"丕丈":4929,"丕丁":2910,"丕乘":689,"丈不":986,"丈丈":10533,"丈丕":5787,"丈丞":4591,"丁休":2124,"丈之":678,"上不":1486,"一位":1048,"丈乘":1046,"丁佐":630,"丈事":641,"丁使":3115,"不丈":1385,"不丁":1326,"不丕":1047,"不不":1140,"不丞":1080,"一丈":689,"丁丕":3008,"丁丞":3158,"丁丈":5062,"丁丁":3771,"丁不":1124,"丁乘":842,"一些":1051,"份、":614,"丈一":1125,"丈丁":5951,"丕樂":705,"主教":1120,"任何":653,"丞業":742,"中文":1114,"人口":1812,"一次":950,"丈林":808,"一條":1013,"之後":1287,"種栽培":2894,"丕於":989,"他們":991,"事場":701,"丞於":627,"丈於":1045,"人使":893,"丁是":707,"丈是":753,"不拔":3356,"二十":705,"人丁":915,"人丈":695,"主席":690,"丁教":802,"丁斯":911,"丁於":991,"丁文":610,"一所":718,"交休":759,"乘大":1193,"事務":628,"不式":1114,"中學":1267,"交不":718,"使。":1730,"使、":1391,"丁店":631,"一座":888,"中央":1281,"丕小":677,"丕屬":955,"事交":1241,"丞家":1096,"丞寫":642,"佐勞":651,"中的":2868,"休如":836,"丈科":1482,"一種":4747,"丞的":2226,"份年":660,"使休":786,"使代":599,"使中":614,"二次":594,"使丈":1261,"使上":902,"使丁":966,"使丞":904,"使丕":680,"下的":914,"世界":3842,"上的":1685,"丈的":3553,"乘江":1087,"佐丞":598,"佐丕":890,"丁的":2951,"佐不":741,"佐丈":1040,"佐丁":1316,"不生":995,"交於":631,"丕的":2516,"不的":1824,"倫。":904,"倫、":1101,"丈爾":927,"丕然":602,"丁爾":1156,"也有":714,"不現":1191,"人工":3084,"丈球":618,"休丈":1588,"休丁":1289,"休丕":1088,"休丞":1470,"以及":5705,"不治":1653,"休倫":752,"也是":2445,"乘斯":612,"休佐":739,"休休":1180,"休使":949,"丁語":647,"交的":662,"何成":648,"丕西":1266,"但是":741,"人的":1304,"丕語":843,"主義":1789,"丁蘭":617,"事的":883,"人物":959,"企業":965,"丁西":590,"中華":3016,"一般":2431,"不聯":718,"人民":2356,"丈至":635,"丈草":589,"使團":1465,"前 ":869,"作家":983,"作品":1437,"使倫":938,"世紀":2133,"亞洲":978,"丁聯":1080,"乘的":932,"到 ":1125,"丞 ":1327,"丕 ":1248,"稱於「":1031,"丈 ":1426,"丈·":665,"丁 ":1214,"丁·":957,"地、":843,"商業":792,"國、":913,"倫，":2201,"又譯":655,"問宮":915,"單位":908,"員會":1240,"可能":966,"南部":1208,"名稱":1366,"參與":743,"各種":710,"名的":1486,"同的":917,"又稱":2281,"使（":775,"使，":3019,"位，":692,"佐，":2446,"台灣":5826,"何，":895,"作，":878,"只有":589,"南等":606,"休（":898,"休，":2604,"同時":1361,"和國":2079,"名於":1540,"在 ":4228,"命名":845,"和丕":658,"和丞":617,"區的":1565,"創辦":644,"和丈":1045,"和丁":617,"前身":709,"交，":1096,"人，":2364,"反應":687,"分類":693,"化的":604,"事，":1473,"勞立":1122,"國王":742,"城事":1733,"因此":1472,"國民":1001,"基丁":1219,"基丞":778,"因於":1311,"多生聞":623,"分，":730,"國大":4188,"四川":1895,"地區":6934,"國國":1282,"在台":591,"國家":4180," 公里":1210,"國丁":723,"國丈":683,"國不":1346,"國人":979,"內，":588,"在丕":590,"在不":766,"在丈":1169,"在丁":857,"地不":1518,"在中":1499,"培。":2897,"保護":897,"公園":1063,"全國":1075,"共和":2094,"共同":713,"公司":6083,"和 ":817,"分丁":734,"勞。":848,"勞、":713,"使蘭":928,"佐責":846,"倫爾":803,"及 ":587,"來自":904,"人類":938,"其他":1807,"公共":721,"倫用":717,"內信":886,"其中":1932,"兩個":962,"倫的":1758,"俄羅":1193,"內丁":817,"交通":965,"代表":1917,"使用":3276,"使理":2623,"來的":817,"使的":2298,"何的":820,"佐的":1260,"作用":690,"之間":1600,"倫州":1179,"作的":823,"何能":735,"倫有":1307,"九龍":820,"倫斯":769,"使究":2861,"倫何":704,"不部":1510,"倫休":862,"代的":605,"倫倫":983,"倫克":676,"使於":674,"使本":654,"位於":6989,"個人":1069,"丁近":678,"作於":1594,"丈車":636,"主要":4266,"一部":1589,"他的":940,"倫丈":1719,"倫丁":1808,"倫丞":1219,"倫丕":1126,"倫中":896,"信息":690,"丈體":712,"倫多":1308,"倫勞":1159,"休畫":658,"人聞":943,"休的":1677,"不面":1013,"及丈":747,"及中":2170,"丕（":1556,"丕，":3869,"下，":946,"上，":1460,"丈（":2498,"丈，":5085,"半島":716,"不，":1457,"一，":2375,"丁）":1026,"丁，":3944,"丁（":1688,"包括":3326,"參加":686,"員。":603,"中，":3370,"及其":661,"創立":812,"原名":722,"丞，":4229,"丞（":1428,"乘，":704,"動物":1355,"又名":874,"勞灣":831,"印度":2180,"可以":2687,"台不":1162,"勞的":1695,"協會":1036,"名使":755,"動畫":650,"合作":595,"包含":733,"南不":932,"公路":1194,"化學":839,"於香港":1347,"利用":694," 世紀":1443,"區域":760,"公里":2070,"內的":698,"倫體":1121,"前尚":2709,"分於":856,"勞丞":1027,"勞休":691,"勞任":888,"勞不":751,"勞丈":1379,"勞丁":1206,"勞丕":1033,"勞倫":1202,"勞佐":918,"名。":909,"分別":960,"利亞":1460,"傳統":899,"共有":696,"具有":1054,"區。":805,"區、":855,"南、":2848,"創作":724,"分布":3537,"全球":780,"加乘":907,"場，":657,"州事":599,"工作":1351,"巴乘":819,"學院":1919,"屬的":3350,"度、":646,"帝國":1099,"工引":2892,"平不":1295,"山谷":592,"年代":1818,"布在":1588,"山西":699,"小都":651,"實際":604,"建、":593,"小說":1488,"巴使":882,"希丕":1033,"尚未":2823,"定的":781,"州、":1207,"地，":4121,"川、":1254,"、雲南":1181,"對於":1252,"它的":613,"學的":914,"山坡":1674,"國，":702,"學生":932,"小的":1375,"山東":747,"屬於":2028,"德·":729,"定義":598,"媒體":593,"就是":946,"家的":1003," 年 ":13455,"形式":845,"形成":781,"德國":1532,"後來":987,"廣播":596,"廣東":1877,"建於":727,"年的":1359,"建立":1105,"引種":2905,"年至":809,"拔 ":3138,"廣乘":652,"外，":1036,"工業":864,"布於":1775,"建佐":1764,"年在":773,"廣州":765,"工程":1106,"已經":809,"常生":722,"廣場":674,"團體":692,"大學":4750,"國際":3079,"名：":4017,"名，":805,"大戰":639,"司，":903,"司（":707,"太平":715,"委員":1628,"多生":1260,"動，":770,"勞，":1822,"國立":626,"國的":3067,"基本":664,"境內":659,"區，":4922,"大利":1318,"大使":1011,"家 ":671,"天休":592,"天主":779,"大丈":858,"大丕":898,"學中":593,"大陸":4384,"學使":615,"安丁":874,"存在":831,"學名":3781,"家丈":660,"家丁":836,"學家":1871,"島、":590,"年 ":13925,"小丕":726,"小丈":935,"家國":1674,"專倫":637,"對係":1024,"尼亞":1180,"學校":1548,"它是":687,"家律":639,"宗教":606,"山丞":856,"大的":1820,"品，":659,"學、":1095,"未由人":2697,"員，":1301,"太空":651,"家、":1074,"家。":1302,"大部":622,"東不":1591,"是由":1946,"有對":649,"於美":890,"最大":1529,"成，":1008,"最早":863,"是美":1276,"日至":621,"最後":917,"時的":620,"朝宮":1146,"林中":937,"林下":865,"林丈":744,"林丕":654,"東南":851,"是於":666,"是日":750,"最丈":682,"教育":1764,"斯特":828,"是指":1896,"服務":1801," 日 ":1059,"時期":1763,"有一":1032,"有丈":631,"栽培":2950,"時間":1470," 月 ":10453,"期的":813,"未由":2698,"有的":742,"東省":644,"是香":1731," 年，":2603," 年）":2399,"有植":939,"有時":596,"會的":752,"於香":1366,"故事":841,"後，":2045,"教丁":618,"教休":765,"文使":808,"、湖不":767,"斯丁":773,"文化":2109,"、江西":640,"於丁":1931,"於一":1279,"於丈":3104,"於不":3971,"於丕":2015,"於丞":1568,"於中":3228,"於主":1138,"式，":713,"於「":3160,"是「":751,"是台":621,"時代":1179,"是在":1454,"東、":1223,"於是":782,"於日":1024,"早期":592,"日本":5548,"於倫":790,"、湖南":720,"名：）":3240,"於了":898,"於人":919,"斯坦":674,"文學":1074,"於台":1510,"數學":761,"於勞":777,"數據":647,"於山":668,"是位":626,"是丕":1220,"是丞":853,"是中":2852,"日在":676,"是丁":1400,"是一":8457,"是不":724,"是丈":2046,"教會":604,"是 ":1586,"推不":777," 年的":915,"或稱":642,"成立":2635,"戰爭":1266,"成的":1247,"日 ":1136,"於 ":12568,"斯·":1030,"所有":1063,"應用":957,"拉丁":1113,"成於":2501,"投資":589,"月 ":10505,"有 ":1922,"技術":1647,"年（":1135,"年）":2513,"年，":3020," 年至":781,"提不":748,"提供":1573,"控制":697,"或者":865,"宮，":689,"家（":883,"家，":2956,"學（":695,"學，":1273,"子，":930,"成。":673,"年間":605,"廣西":1228," 年在":693,"屬（":1280," 年代":1445," 平不":1026,"成員":1192,"所以":843,"成何":668,"影響":1080,"小，":1059,"委員會":1211,"流行":628,"業，":586," 日）":775," 日，":1367,"源於":682,"爾·":762,"沒有":1285,"活動":1238,"比賽":1111,"江蘇":807,"江西":972,"湖不":1117,"湖南":1294,"江、":1010,"斯（":607,"文：":2388,"機構":1217,"死對":1361,"、廣東":743,"日，":1544,"日）":813,"歷使":2356," 日至":616,"民國":1569,"歐洲":1588,"民主":899,"民共":1266,"正式":1274,"時，":1278,"河南":853,"月，":734,"、廣西":861,"會，":853,"會（":980,"民族":1066,"期，":613,"河不":810,"根據":1260,"會議":766,"最高":966,"期間":1013,"有限":1519,"標佐":1052,"植物":4908," 是一":681,"概念":627," 日在":656,"的電":999,"稱「":1043,"的西":633,"發行":1127,"的重":753,"第 ":1807,"的發":596,"的第":1621,"物，":2112,"目的":1040,"的是":1255,"的最":739,"的植":2894,"直接":612,"發現":996,"的特":1537,"積 ":785,"發生":1316,"的對":648,"的小":1527,"的家":632,"發展":2338,"的大":1229,"的國":1195,"的地":4227,"目前":4386,"的丁":3310,"的一":9461,"用的":1238,"生的":842,"產生":949,"生產":964,"球隊":888,"生物":1143,"生聞":4477,"甘肅":1049,"的名":796,"的勞":1368,"的倫":1653,"的休":1719,"的使":1916,"的佐":1046,"的作":651,"的主":1361,"的中":1197,"的丕":3244,"的丞":2994,"的丈":5094,"的不":2456,"的乘":747,"的人":1899,"的交":1021,"生於":2502,"用於":1261,"由於":1686,"理論":1080,"當時":1405,"生活":843,"生在":746,"產品":771,"的。":900,"的《":764,"的「":1273,"環境":892,"由人":2997,"用來":777,"理學":1070,"現在":1079,"王朝":657,"現代":897,"獲得":1128,"的 ":1662,"用。":731,"班丁":801,"物理":701,"特有":1087,"特別":1033,"澳門":921,"、福建":587,"物。":3616,"聯合":1423,"而成":666,"聞在":1114,"等，":840,"聞於":3447,"肅、":797,"網路":1657,"總統":750,"稱，":608,"種，":743,"美國":6254,"有限公":1342,"義大":928,"群島":661,"羅斯":1391,"聯事":701,"美洲":846,"站，":1417,"站（":605,"聯休":1628,"立，":947,"經濟":1788,"統的":590,"經營":801,"、甘肅":803,"線的":712,"至 ":5663,"自 ":699,"紀念":700,"簡稱":3399,"組成":1456,"。由於":638,"聞 ":661,"米的":3024,"結構":812,"米至":2731,"系統":2899,"統治":615,"目，":621,"結丁":586,"組佐":2037,"約丈":598,"系使":1485,"節目":923,"立於":1349,"等地":3334,"的，":1232,"天主教":743,"立的":1251,"生，":616,"用，":772,"程式":650,"科技":622,"約 ":1720,"第三":1132,"第一":3441,"第二":2120,"稱於":4215,"種栽":2894,"科丈":1047,"等。":1259,"科學":1716,"福建":1133,"社會":2251,"站。":627,"角色":606,"計算":1063,"設立":673,"西部":622,"製造":737,"認於":1497,"西班":773,"要的":1104,"被稱":1048,"計劃":875,"越南":953,"資料":957,"賽事":631,"語言":1720,"設計":1777,"號，":798,"處，":614,"譯於":650,"超過":651,"路線":849,"足球":1703,"資訊":664,"行，":1162,"醫學":647,"進行":2272,"都是":704,"過程":791,"這種":792,"部分":2342,"部份":776,"遊戲":1924,"連接":662,"通常":1653,"運動":2496,"語：":3929,"說，":690,"車站":2410,"這個":1488,"這些":923,"於日本":917,"自治":728,"自然":792,"英國":2374,"自由":877,"般生":678,"線，":642,"航空":1143,"草地":752," 米的":2958,"自丁":786,"羅馬":1149,"與丈":666," 米至":2728,"米，":753,"聯賽":916,"華民":1238,"英語":2016,"者，":759,"舉行":1293,"英文":2836,"舉辦":651,"華人":1471,"著名":1732,"蘇聯":599,"處理":911,"藝術":1217,"行。":771,"聞，":628,"行於":853,"製作":1162,"西南":747,"行的":1255,"西份":1005,"西亞":1235,"西不":1211,"行不":2204,"語 ":675,"西、":2735,"中，目":813,"是位於":586,"間，":1121,"是一種":2255,"香港":8631,"高丁":607,"體的":647,"隊，":588,"高速":865,"體育":810,"及中國":2028,"公里，":1100,"體，":795,"是一個":2235,"丈（學":765,"是中國":2143,"於台灣":1145,"選舉":733,"通過":1270,"部的":1066,"賽，":689,"路，":930,"重要":1746,"銀行":879,"鐵家":726,"的第一":601,"重要的":694,"開始":2056,"部，":1123,"除了":587,"限公":1343,"鐵路":1902,"電勞":1154,"雲南":1736,"阿拉":770,"間的":1117,"開發":1451,"陸的":3080,"里，":1236,"電影":2042,"阿爾":603,"電子":1071,"面積":1525,"非洲":681,"領域":708,"項目":726,"電視":2609,"音樂":1761,"需要":625,"馬來":712,"有植物":938,"的特有":970,"是美國":1183,"的植物":2889,"日至 ":606,"前尚未":2703,"最大的":952,"於美國":799,"加乘大":716,"是日本":699,"目前尚":2707,"的地區":3107,"生聞在":1091,"生聞於":3237,"甘肅、":794,"的一部":774,"的主要":668,"的一種":1474,"年），":737,"的一個":3094,"限公司":1342,"年（ ":710,"於不拔":2919,"於中國":2310," ，是":653,"南等地":586,"），":14128,"（）":3756,"（，":1173,"，）":1558,"：，":731,"：）":4068,"由人工":2898,"，東":861,"，有":1487,"，最":1123,"，曾":1063,"，是":13163,"）是":10839,"，於":6392,"，此":660,"，後":1253,"，從":882,"，常":1047,"，故":644,"）於":2446,"，指":584,"，所":993,"，或":1331,"，成":1293,"）的":2203,"，目":3631,"，簡":2031,"，第":778,"，現":1338,"，由":3905,"，用":642,"，生":3524,"，當":880,"，西":834,"，被":860,"，該":1017,"，經":598,"，總":744,"，美":597,"，而":3222,"，英":973,"，與":1255,"（英":2412,"，香":721,"，通":885,"，這":1582,"，「":615,"，《":690,"）。":3711,"）、":2876,"（學":3641,"，它":1379,"，屬":841,"，小":787,"，對":650,"，因":2415,"，在":4525,"，多":1566,"，大":803,"，如":966,"，前":662,"，分":861,"，南":727,"，即":1028,"，勞":1219,"，包":1288,"）和":952,"，同":897,"，台":652,"，可":1102,"，又":2944,"，原":1271,"，不":2771,"，丕":3583,"，丞":2297,"，並":3993,"，中":1698,"，主":1659,"（今":666,"，乘":1385,"，也":3255,"（丈":751,"，丈":5090,"，丁":3996,"，一":2348,"，休":1371,"，但":3353,"，位":2751,"，佐":784,"，使":1949,"，交":834,"，亦":1195,"，人":871,"，以":3497,"，他":1340,"，份":756,"，倫":1535,"，共":754,"，其":3556,"，全":1257,"（ ":3933,"） ":996,"， ":7569,"－ ":815,"雲南、":1086,"丁屬（":787,"華民國":1215,"廣西、":800,"中國的":1325,"中國大":3838,"之一，":2265,"英語：":1339,"不拔 ":3137,"引種栽":2892,"丈屬的":703,"人工引":2892," ），":596,"乘江、":593,"特有植":935,"以及中":1990,"一般生":678,"中華人":1156,"英文：":1510,"丕西、":804,"中華民":1237,"廣東、":761,"華人民":1156,"人民共":1261,"：）於":1432,"：）是":1898,"），又":978,"），是":2411,"（）是":1113,"，），":1004,"著名的":780,"（），":1524,"位於香":588,"年至 ":713,"面積 ":770,"倫州、":844,"之間的":628,"成立於":922,"內丁使":611,"俄羅斯":1193,"，香港":708,"物。分":2798,"公司（":691,"公司，":864,"行不區":1022,"共和國":1943,"分布於":1717,"分布在":1578,"》、《":944,"」、「":864,"，於中":674,"）是丈":645,"）是一":2670,"，是一":2178,"，是中":1286,"湖南、":689,"あああ":1321,"尚未由":2697,"地，生":2880,"，常生":667,"，於 ":2197,"，所以":698,"，又稱":1386,"，因此":1151,"，多生":1249,"聞於不":2897,"（學名":3634,"。分布":2903,"、印度":793,"、乘江":625,"、丕西":798,"、倫州":850,"、山坡":668,"被稱於":856,"、四川":1250,"大陸的":3064,"アアア":1275,"學名：":3509,"（英語":1020,"（英文":1336,"義大利":914,"，目前":3420,"西班丁":773,"，生聞":2926,"，簡稱":1929,"平不公":818,"工引種":2892,"，包括":1128,"米的地":2889,"，又名":585,"，在 ":642,"，其中":943,"，以及":1003,"，也是":1481,"，一般":1212,"，主要":1207,"，位於":2550,"，並丁":649,"，中國":911,"屬的植":2808,"丁使、":633,"丈丈丁":628,"江西、":618,"湖不、":763,"不同的":723,"米至 ":2729,"之一。":1752,"不公里":761,"丈丈，":616},"n_words":[4924775,1867501,309785],"name":"zh-tw"}
\ No newline at end of file
text/langdetect/utils/lang_profile.py 0 → 100644
View file @ b309ea1b
from collections import defaultdict
import re
import six
from six.moves import xrange
from .ngram import NGram
class LangProfile(object):
MINIMUM_FREQ = 2
LESS_FREQ_RATIO = 100000
ROMAN_CHAR_RE = re.compile(r'^[A-Za-z]$')
ROMAN_SUBSTR_RE = re.compile(r'.*[A-Za-z].*')
def __init__(self, name=None, freq=None, n_words=None):
self.freq = defaultdict(int)
if freq is not None:
self.freq.update(freq)
if n_words is None:
n_words = [0] * NGram.N_GRAM
self.name = name
self.n_words = n_words
def add(self, gram):
'''Add n-gram to profile.'''
if self.name is None or gram is None: # Illegal
return
length = len(gram)
if length < 1 or length > NGram.N_GRAM: # Illegal
return
self.n_words[length - 1] += 1
self.freq[gram] += 1
def omit_less_freq(self):
'''Eliminate below less frequency n-grams and noise Latin alphabets.'''
if self.name is None: # Illegal
return
threshold = max(self.n_words[0] // self.LESS_FREQ_RATIO, self.MINIMUM_FREQ)
roman = 0
for key, count in list(six.iteritems(self.freq)):
if count <= threshold:
self.n_words[len(key)-1] -= count
del self.freq[key]
elif self.ROMAN_CHAR_RE.match(key):
roman += count
# roman check
if roman < self.n_words[0] // 3:
for key, count in list(six.iteritems(self.freq)):
if self.ROMAN_SUBSTR_RE.match(key):
self.n_words[len(key)-1] -= count
del self.freq[key]
def update(self, text):
'''Update the language profile with (fragmented) text.
Extract n-grams from text and add their frequency into the profile.
'''
if text is None:
return
text = NGram.normalize_vi(text)
gram = NGram()
for ch in text:
gram.add_char(ch)
for n in xrange(1, NGram.N_GRAM+1):
self.add(gram.get(n))
text/langdetect/utils/messages.properties 0 → 100644
View file @ b309ea1b
NGram.CJK_KANJI_EXCLUDE=\u0020\uFF08\uFF09
NGram.LATIN1_EXCLUDE=\u00A0\u00AB\u00B0\u00BB
NGram.KANJI_1_0=\u4F7C\u6934
NGram.KANJI_1_2=\u88CF\u95B2
NGram.KANJI_1_4=\u7027\u7DCB
NGram.KANJI_1_8=\u4E80\u4E9C\u4EEE\u5263\u5264\u5270\u52C5\u52E7\u52F2\u53B3\u5449\u58CA\u58CC\u5968\u59C9\u59EB\u5D8B\u5DE3\u5E30\u6075\u622F\u623B\u6255\u629C\u629E\u62DD\u62E1\u633F\u635C\u63FA\u6442\u6589\u658E\u6669\u66A6\u66FD\u6804\u685C\u6B69\u6B6F\u6BBB\u6C37\u6C5A\u6D44\u6E09\u6E0B\u6E13\u6EDD\u713C\u72A0\u731F\u7363\u7A32\u7A42\u7A93\u7ADC\u7C8B\u7C9B\u7DD1\u7E01\u7E04\u7E26\u7E4A\u7E4B\u7E70\u8074\u8107\u8133\u81D3\u820E\u8217\u8358\u83D3\u85AC\u8987\u899A\u8B21\u8B72\u8B83\u8CDB\u9045\u90F7\u91C8\u9271\u9283\u92AD\u9665\u967A\u96A0\u96A3\u96B7\u970A\u983C\u9854\u9855\u99C6\u9A12\u9ED9\u9F62
NGram.KANJI_1_11=\u67D8\u831C
NGram.KANJI_1_12=\u5742\u57FC\u5800
NGram.KANJI_1_13=\u4E3C\u4E98\u4FE3\u4FF5\u5072\u51A8\u53A9\u5451\u546A\u5504\u5516\u55A9\u55B0\u5618\u5642\u565B\u567A\u56A2\u57F4\u5840\u5841\u58F1\u59F6\u5A2F\u5B22\u5B8D\u5DCC\u5EFB\u5F10\u60A9\u60E3\u61D0\u62F6\u63B4\u63BB\u63C3\u6681\u685F\u6955\u6962\u696F\u698A\u698E\u69FB\u6A2B\u6A7F\u6B53\u6BD8\u6D99\u6E07\u7460\u7473\u7560\u7573\u758E\u7690\u7815\u783A\u7962\u7A4F\u7A63\u7AEA\u7BED\u7CA7\u7D18\u7D3A\u7E4D\u8061\u8218\u8276\u82C5\u8597\u85AB\u86CD\u874B\u88FE\u8ACF\u8B90\u8D0B\u8FBF\u9013\u9061\u914E\u9154\u918D\u9190\u91A4\u91B8\u9262\u929A\u92ED\u92F3\u932C\u96EB\u96F0\u976D\u97EE\u981A\u99C4\u9A28\u9AC4\u9B8E\u9C10\u9D0E\u9D5C\u9D8F\u9E78\u9EB9\u9EBA\u9EBF
NGram.KANJI_1_14=\u5F66\u7984\u7985
NGram.KANJI_1_16=\u5861\u7B25\u844E\u9419\u9D07
NGram.KANJI_1_18=\u5039\u514E\u51E7\u51EA\u5301\u5302\u5859\u58F7\u59AC\u5C2D\u5CA8\u5EFC\u6357\u64B9\u67CA\u6802\u6834\u68BC\u6900\u6919\u691B\u69D9\u6AE8\u6D9C\u6E8C\u6F09\u6F45\u701E\u7026\u7114\u72DB\u7577\u75E9\u783F\u7895\u7A50\u7AC3\u7B48\u7B86\u7BAA\u7C7E\u7C82\u7C8D\u7CCE\u7D2C\u7F6B\u7FEB\u8557\u85AE\u86CE\u877F\u8997\u8ACC\u8CB0\u8CCE\u8FE9\u9197\u920E\u9266\u927E\u92F2\u9306\u9453\u9784\u982C\u9834\u99C8\u9BF5\u9C2F\u9D2C
NGram.KANJI_1_22=\u6762\u6A17\u887F
NGram.KANJI_1_27=\u4E21\u4E57\u4ECF\u4F1D\u4FA1\u4FF3\u5024\u50CD\u5150\u5186\u51E6\u52B4\u52B9\u5358\u53CE\u55B6\u56E3\u56F2\u56F3\u570F\u5727\u5869\u5897\u58F2\u5909\u5B9F\u5BDB\u5BFE\u5C02\u5DFB\u5E2F\u5E81\u5E83\u5EC3\u5F3E\u5F93\u5FB3\u5FB4\u5FDC\u60AA\u6226\u6238\u6271\u62E0\u6319\u63B2\u6483\u64AE\u67A0\u67FB\u691C\u697D\u69D8\u6A29\u6B73\u6B74\u6BCE\u6C17\u6CA2\u6D5C\u6E08\u6E80\u702C\u7523\u767A\u770C\u7D4C\u7D75\u7D76\u7D99\u7D9A\u7DCF\u8535\u8846\u89A7\u89B3\u8A33\u8AAC\u8AAD\u8C4A\u8EE2\u8EFD\u8FBA\u8FBC\u9244\u9332\u95A2\u95D8\u96D1\u99C5\u9A13\u9ED2
NGram.KANJI_1_29=\u4F0E\u4FFA\u5036\u53E1\u54B2\u5506\u583A\u5C3B\u5CAC\u5CE0\u5CEF\u6803\u68B6\u6A0B\u6A8E\u73C2\u7551\u7826\u7881\u79B0\u7B39\u8429\u8599\u8FBB\u9162\u95C7\u9688\u96BC\u9AEA\u9DF2
NGram.KANJI_1_31=\u5553\u938C
NGram.KANJI_1_35=\u51B4\u564C\u57DC\u5B2C\u6822\u685D\u690B\u6973\u6C93\u7511\u7887\u7A17\u83D6\u847A\u8494\u8526\u854E\u85C1\u86F8\u88B4\u93A7\u9B92\u9C39\u9C48\u9C52
NGram.KANJI_2_0=\u4E2B\u4EC3\u4F09\u4F57\u4F6F\u4F70\u4FD1\u4FDA\u500C\u5043\u516E\u5189\u5241\u530D\u5310\u5412\u54AB\u54AF\u5514\u5556\u55B1\u561F\u573B\u586D\u587D\u58C5\u58D1\u5914\u5A62\u5A6A\u5AE6\u5B40\u5B5B\u5B70\u5BB8\u5CD2\u5D01\u5D34\u5E11\u5EA0\u5F0B\u5F2D\u5F87\u607F\u621B\u6221\u6289\u63A3\u6452\u646D\u64D8\u652B\u6600\u6631\u6641\u66F7\u6773\u67B8\u67DD\u67DE\u6829\u68FB\u69AD\u6A47\u6C10\u6C68\u6C74\u6C85\u6CD3\u6D31\u6D93\u6D94\u6DB8\u6DBF\u6DC5\u6E6E\u6EA7\u6EB4\u6EC2\u6F2A\u6F2F\u6FB9\u6FC2\u6FDB\u6FEE\u70AF\u70FD\u7166\u726F\u729B\u739F\u73DE\u740A\u746D\u749C\u749F\u74E0\u759D\u75A3\u75CD\u75DE\u7600\u7620\u7688\u7738\u7762\u776B\u777D\u77E3\u781D\u7837\u78A3\u7946\u7B60\u7F44\u7F54\u7F5F\u7FAF\u8026\u807F\u80C4\u80DB\u80ED\u81E7\u824B\u82B7\u82E3\u8392\u846D\u84D3\u8548\u85B9\u86DE\u873F\u8753\u8782\u87AB\u87B3\u87D1\u87E0\u87FE\u8821\u88D8\u88E8\u8913\u891A\u892B\u8983\u8C3F\u8C49\u8C82\u8D6D\u8DE4\u8E1D\u8E1E\u8E7C\u8FE5\u8FE8\u9005\u9035\u9050\u9082\u9083\u9095\u90E2\u911E\u91AE\u91B4\u93D6\u9621\u968D\u96B9\u96D2\u9711\u9713\u973E\u9AB0\u9AB7\u9AE6\u9B03\u9B23\u9EDC\u9EEF
NGram.KANJI_2_1=\u4E82\u4F48\u4F54\u50F9\u5167\u528D\u52DE\u532F\u537B\u53C3\u5433\u555F\u55AE\u56B4\u570D\u5716\u58D3\u58DE\u5920\u5967\u5A1B\u5BEB\u5BEC\u5C08\u5C0D\u5C46\u5C6C\u5CFD\u5E36\u5E6B\u5EC8\u5EF3\u5F48\u5F91\u5F9E\u5FB5\u6046\u60E1\u61F7\u6232\u6236\u64C7\u64CA\u64D4\u64DA\u64F4\u651D\u6578\u65B7\u6649\u6A13\u6A23\u6A6B\u6A94\u6AA2\u6B0A\u6B50\u6B61\u6B72\u6B77\u6B78\u6C92\u6EAB\u6EFF\u6FD5\u6FDF\u71DF\u722D\u72C0\u734E\u737B\u746A\u7522\u773E\u78BC\u7A69\u7C3D\u7CB5\u7D55\u7D72\u7DA0\u7DAB\u7DE3\u7E5E\u7E6A\u7E7C\u7E8C\u8072\u807D\u8085\u812B\u8166\u8173\u81D8\u8209\u820A\u8332\u838A\u840A\u85E5\u860B\u8655\u865B\u88DD\u89BA\u89BD\u89C0\u8AAA\u8B6F\u8B7D\u8B8A\u8B93\u8C50\u8CF4\u8E64\u8F15\u8F49\u8FA6\u8FAD\u9109\u9130\u91AB\u91CB\u92B7\u9304\u9322\u95CA\u96A8\u96AA\u96B1\u96B8\u96D6\u96D9\u96DC\u9748\u975C\u986F\u9918\u99DB\u9A57\u9B25\u9EA5\u9EC3\u9EDE\u9F52
NGram.KANJI_2_4=\u514C\u51AA\u5614\u56AE\u56C2\u582F\u58FA\u5B0C\u5D11\u5DD2\u5DD6\u5E40\u5E5F\u5EEC\u6137\u6417\u6488\u64F2\u652A\u6582\u6689\u689F\u68D7\u69D3\u6A97\u6AB8\u6ABB\u6AC3\u6ADA\u6B7F\u6BB2\u6EA5\u6EC4\u6EF2\u7009\u701D\u7028\u703E\u7165\u71BE\u721B\u7463\u7464\u7469\u7515\u7526\u75FA\u7621\u779E\u79B1\u7A1F\u7AC4\u7AC7\u7B8F\u7BE9\u7D2E\u7D68\u7D8F\u7DB8\u7DBA\u7E46\u7E79\u7F4C\u7F88\u8070\u8073\u8076\u81BE\u82BB\u83A2\u858A\u8591\u861A\u8778\u87EC\u8805\u880D\u893B\u8A1B\u8A25\u8A36\u8A85\u8AA6\u8B17\u8B28\u8CB6\u8CE4\u8D16\u8D1B\u8ECB\u9112\u9214\u9249\u93AC\u9594\u9598\u95BB\u95D5\u965E\u96B4\u97DC\u9821\u9824\u9921\u9952\u9A55\u9A5B\u9B1A\u9C13\u9D09\u9DAF\u9E1A\u9E75\u9F67
NGram.KANJI_2_9=\u4E9F\u4F6C\u4FDE\u4FFE\u5029\u5140\u51A2\u5345\u539D\u53FB\u54C7\u5599\u560E\u561B\u563B\u566C\u5676\u5729\u574D\u57E4\u595A\u598D\u5A1F\u5A25\u5A77\u5AB2\u5AD6\u5BF0\u5C2C\u5CEA\u5E37\u5F08\u6059\u606A\u6096\u609A\u62A8\u6555\u6556\u66E6\u675E\u68E3\u69BB\u6BCB\u6BD3\u6C1F\u6C26\u6C81\u6DC4\u6DDE\u6E32\u6E44\u6E4D\u6F33\u6F7C\u6FA7\u701A\u701B\u715C\u741B\u7428\u7480\u74A8\u7504\u752C\u768B\u76CE\u78CA\u78FA\u79BA\u7C27\u8046\u81FB\u8331\u8393\u83C1\u8403\u8438\u843C\u8446\u85B0\u87D2\u8862\u8DC6\u9074\u9131\u9672\u96EF\u9704\u9706\u977C\u9ABC\u9E92\u9ECF
NGram.KANJI_2_10=\u51BD\u5704\u7350\u73A5
NGram.KANJI_2_11=\u4E15\u4EA2\u4F5A\u50D6\u5349\u53DF\u5484\u5958\u5B34\u5B5A\u5C91\u5E1B\u5F77\u61CB\u61FF\u620C\u620D\u622E\u6248\u6538\u660A\u664F\u678B\u67E9\u69B7\u69C3\u6CB1\u6CD7\u6D5A\u6DAA\u6DC7\u7099\u71EE\u7325\u7425\u7455\u747E\u749E\u75B5\u7678\u7693\u76C2\u77B0\u77BF\u78CB\u7957\u795A\u797A\u7A79\u7B08\u7B75\u7BB4\u7F9A\u7FB2\u7FDF\u80E5\u81BA\u8340\u837C\u8398\u8559\u85A8\u86DF\u8734\u8882\u88F4\u8936\u900D\u907D\u9642\u96C9\u9AFB\u9E9D\u9EBE
NGram.KANJI_2_12=\u5F57\u7940
NGram.KANJI_2_13=\u5191\u7791\u792C\u7D46
NGram.KANJI_2_15=\u5713\u58FD\u5D17\u5D19\u5DBC\u5F4C\u6191\u64A5\u687F\u69AE\u6AFB\u6EEC\u6F3F\u6FE4\u6FF1\u6FFE\u700B\u74CA\u76E1\u76E7\u7926\u792B\u79AE\u7AA9\u7C43\u7C4C\u7C64\u7DBD\u81A0\u856D\u8594\u8606\u8A62\u8AF7\u8CC8\u8CE3\u8D99\u8F1B\u8F3B\u9059\u9127\u9264\u947D\u95A9\u97CB\u980C\u9838\u9846\u99AE\u9A19\u9B06\u9B91\u9F4A\u9F4B
NGram.KANJI_2_16=\u4E69\u4EC4\u4EDF\u4EF3\u4F0B\u4F5E\u5000\u5028\u50E5\u513B\u5157\u51DC\u52D7\u530F\u5379\u53F5\u5471\u5477\u5555\u555C\u557B\u5594\u55B2\u55C9\u560D\u5616\u562E\u5630\u5653\u5657\u566F\u56A8\u56B6\u5820\u5880\u58CE\u58D9\u5950\u5969\u596D\u599E\u59B3\u59CD\u59D2\u5A40\u5AA7\u5ABC\u5AD7\u5AD8\u5B0B\u5B24\u5B38\u5B53\u5C5C\u5D06\u5D47\u5D94\u5D9D\u5E57\u5EC4\u5F46\u5FAC\u60BD\u60D8\u6123\u615D\u615F\u6175\u618A\u61AB\u61E3\u623E\u6308\u636B\u645F\u6519\u6595\u6698\u66B8\u67D9\u6840\u695D\u696E\u6979\u69C1\u69E8\u6AEC\u6AFA\u6B5F\u6CAC\u6CE0\u6CEF\u6D0C\u6D36\u6DD2\u6DD9\u6DE6\u6DEC\u6E5F\u6FA0\u6FEC\u7156\u71C4\u71DC\u71EC\u71FC\u720D\u7230\u7292\u7296\u72A2\u72CE\u7357\u737A\u7380\u7386\u73A8\u73EE\u743F\u74A6\u74CF\u74D4\u74DA\u755A\u75A5\u75B3\u75C2\u75E0\u75F1\u75FF\u7601\u7609\u7646\u7658\u769A\u76B0\u774F\u775C\u778B\u77BD\u77C7\u7843\u787F\u78F4\u79C8\u7A88\u7A95\u7AFD\u7B1E\u7B67\u7B9D\u7BCC\u7C0D\u7C11\u7C37\u7C40\u7C6E\u7CB3\u7CBD\u7D09\u7D31\u7D40\u7D5B\u7D70\u7D91\u7D9E\u7DB0\u7DD9\u7DF9\u7E08\u7E11\u7E1D\u7E35\u7E52\u7FB6\u7FBF\u7FEE\u8012\u801C\u8028\u8052\u8123\u8188\u81C3\u81DA\u81FE\u8210\u82BE\u83A0\u83D4\u8407\u8435\u8477\u849E\u84C6\u84CA\u85F9\u867A\u86B5\u86B6\u86C4\u8706\u8707\u870A\u8768\u87BB\u8831\u8839\u8879\u8921\u8938\u8964\u89A6\u89AC\u8A10\u8A3E\u8AC2\u8ADB\u8AF3\u8B2B\u8B41\u8B4E\u8B5F\u8B6B\u8B92\u8C55\u8C62\u8C73\u8C8A\u8C8D\u8CB2\u8CB3\u8CD2\u8CE1\u8CFB\u8D0D\u8E34\u8E7A\u8E8A\u8ED4\u8EFE\u8F0A\u8F1C\u8F1E\u8F26\u8FAE\u9088\u90C3\u90FE\u9134\u9148\u91D9\u91E9\u9238\u9239\u923D\u924D\u925A\u9296\u92AC\u92BB\u9315\u9319\u931A\u9321\u9370\u9394\u93A2\u93D8\u93E4\u943A\u9477\u9582\u958E\u95A1\u95C8\u95CC\u95D4\u9658\u966C\u970F\u973D\u9744\u975B\u9766\u97A3\u97A6\u97C1\u97C6\u980A\u9837\u9853\u9870\u98AF\u98B3\u98BA\u98E9\u98ED\u9912\u991B\u991E\u993D\u993F\u99D1\u99DF\u9A01\u9A3E\u9A43\u9A4D\u9ACF\u9AE1\u9B22\u9B58\u9C25\u9C3E\u9C54\u9C56\u9D15\u9D23\u9D89\u9DC2\u9DD3\u9E82\u9E8B\u9EA9\u9EE0\u9EF7\u9F07\u9F2F\u9F34\u9F3E\u9F5F\u9F6C
NGram.KANJI_2_18=\u5155\u520E\u55DF\u56C0\u56C1\u5793\u5FD6\u5FF8\u6029\u60FA\u613E\u6147\u615A\u62C8\u6384\u6883\u6894\u68F9\u6AA3\u6AAE\u6AC2\u6E63\u7032\u70A4\u7146\u71FB\u7228\u72F7\u7370\u7441\u74BF\u75B8\u75E3\u7622\u76CD\u7768\u79E3\u7A60\u7B6E\u7BC1\u7C5F\u7D06\u7E2F\u7E39\u8146\u81CF\u8703\u8729\u8737\u87EF\u88D2\u8A22\u8AC4\u8AF6\u8E59\u8F33\u8F42\u9169\u91B1\u9278\u93C3\u93DD\u9460\u946A\u9785\u9AD1\u9B4D\u9B4E\u9C31\u9D12\u9ECC
NGram.KANJI_2_21=\u502A\u544E\u59AE\u59EC\u5D1B\u66A8\u6BD7\u6C76\u6E1D\u70EF\u742A\u7459\u7FE1\u82EF\u8343\u85C9\u8A79\u90DD
NGram.KANJI_2_22=\u4EDE\u4F7B\u504C\u50EE\u52E3\u52F0\u536E\u54A9\u54BB\u54BF\u54C2\u54E6\u550F\u556A\u55E8\u564E\u5664\u5671\u568F\u56DD\u572F\u57A0\u5809\u5924\u59A3\u59A4\u59E3\u5A13\u5A23\u5B51\u5B73\u5C50\u5C8C\u6035\u60C6\u6106\u6215\u62CE\u62FD\u64ED\u6549\u6554\u655D\u659B\u65CE\u65D6\u6615\u6624\u665E\u6677\u669D\u66E9\u6772\u677C\u696B\u6A84\u6AA0\u6BFD\u6C16\u6C86\u6C94\u6CD6\u6D2E\u6D39\u6F78\u6FB6\u705E\u70CA\u7168\u723B\u7256\u7284\u73B3\u740D\u742F\u7498\u74A9\u752D\u75F3\u7634\u768E\u76B4\u76E5\u77A0\u77DC\u781F\u782D\u7AA0\u7BFE\u7FF1\u80AB\u8174\u81EC\u8202\u8222\u8228\u82DC\u8306\u83FD\u8469\u84FF\u859C\u8617\u86B1\u8722\u8C89\u8D67\u8DCE\u8E49\u8E76\u8E87\u8FE2\u8FE4\u8FF8\u9016\u905B\u9174\u982B\u98E7\u9955\u9B32
NGram.KANJI_2_23=\u4F8F\u5055\u524C\u548E\u5583\u594E\u5CB7\u5ED6\u5F5D\u6021\u66B9\u66F0\u6C55\u6C7E\u6C82\u6E2D\u6EC7\u6ED5\u70B3\u71B9\u72C4\u73C0\u7426\u745C\u748B\u7696\u777F\u79A7\u79B9\u7F8C\u8153\u8339\u8386\u8725\u90B5\u9102\u962E\u9716\u97F6
NGram.KANJI_2_28=\u5733\u57D4\u838E\u8FEA
NGram.KANJI_2_29=\u50ED\u5F29\u62EE\u6A9C\u7BC6\u80F1\u8129\u8171\u822B\u8AEB
NGram.KANJI_2_30=\u4EB3\u4F15\u4FB7\u5006\u509A\u50A2\u5102\u5109\u5115\u5137\u5138\u513C\u524B\u524E\u5277\u528A\u52E6\u52FB\u5331\u5436\u5443\u54FD\u5538\u555E\u55C6\u55C7\u5679\u5690\u5695\u56C9\u56D1\u56EA\u588A\u58E2\u5AFB\u5B2A\u5B43\u5B7F\u5BE2\u5C37\u5D27\u5D84\u5D87\u5DD4\u5EC1\u5EDD\u5F12\u5FA0\u60F1\u616B\u61F5\u61F6\u61FE\u62DA\u6371\u6399\u63C0\u6451\u647B\u6493\u64BB\u64BF\u64C4\u64F1\u64F7\u650F\u652C\u665D\u6684\u6688\u66EC\u672E\u68E7\u69A6\u69ED\u69F3\u6A01\u6AAF\u6AE5\u6BA4\u6BAE\u6BAF\u6BC6\u6C08\u6C2C\u6C59\u6D87\u6EBC\u6ECC\u6EF7\u6F6F\u6F80\u6F86\u6FD8\u6FF0\u6FFA\u7006\u7018\u7030\u7051\u7192\u71C9\u71D9\u71F4\u71FE\u7274\u7377\u74A3\u750C\u7613\u7627\u7661\u7662\u7665\u766E\u7671\u7672\u76BA\u775E\u776A\u778C\u78E7\u7955\u7A08\u7AC5\u7B4D\u7C2B\u7C6C\u7CF0\u7D02\u7D1C\u7D73\u7DA2\u7DB5\u7DDE\u7E09\u7E0A\u7E37\u7E43\u7E61\u7E7D\u7E93\u7F3D\u7FF9\u81A9\u8271\u83F8\u84C0\u8514\u85BA\u86A9\u86FB\u879E\u8814\u8836\u889E\u8932\u896A\u896F\u8993\u89B2\u8A15\u8A16\u8A1D\u8A5B\u8A6C\u8A6D\u8A7C\u8AA1\u8AA3\u8AA5\u8B0A\u8B4F\u8B59\u8B96\u8C48\u8C54\u8CBD\u8CFA\u8D13\u8E89\u8E8B\u8EAA\u8EC0\u8EDB\u8EFC\u8F12\u8F1F\u8F3E\u8F45\u8FFA\u9015\u9183\u919E\u91A3\u91D7\u91F5\u9209\u9215\u923E\u9240\u9251\u9257\u927B\u9293\u92A8\u92C5\u92C7\u92F0\u9333\u935A\u9382\u938A\u9398\u93B3\u93D7\u93DF\u93E2\u93FD\u942B\u942E\u9433\u9463\u9470\u9472\u947E\u95D0\u96CB\u97C3\u97CC\u981C\u9839\u986B\u98B6\u98EA\u9909\u991A\u9935\u993E\u9951\u99A5\u99B1\u99D9\u99DD\u99F1\u9A2B\u9A62\u9A65\u9AAF\u9AD2\u9AEF\u9B0D\u9B28\u9B77\u9BFD\u9C49\u9C5F\u9C78\u9D3F\u9D72\u9DD7\u9E1B\u9EB4\u9EF4\u9F66\u9F94
NGram.KANJI_2_31=\u5DBD\u63C6\u6E3E\u7587\u8AF1\u8B5A\u9695
NGram.KANJI_2_32=\u53A5\u589F\u5CD9\u7109\u7F79\u8006\u8654\u8944\u968B\u96CD
NGram.KANJI_2_35=\u4F47\u4F91\u4FCE\u4FDF\u527D\u535E\u55DA\u56A5\u5879\u5A11\u5B7A\u5CAB\u5CF4\u5EBE\u5F7F\u5FA8\u601B\u606B\u60B8\u610D\u6134\u619A\u61FA\u6369\u6523\u65CC\u66C4\u6727\u6968\u6A05\u6A48\u6B59\u6BEC\u6D35\u6D38\u6E19\u701F\u7064\u711C\u716C\u71A8\u71E7\u7258\u743A\u746F\u75BD\u75D9\u75F2\u7669\u766C\u76DE\u7729\u77BC\u78EC\u792A\u7A37\u7A62\u7BE6\u7C2A\u7C50\u7D07\u7DD8\u7E5A\u7F8B\u7FD5\u7FF3\u8151\u81CD\u8317\u83F4\u85EA\u85FA\u8823\u895E\u89F4\u8A0C\u8A41\u8AA8\u8ACD\u8B10\u8CC1\u8D05\u8D73\u8E4A\u8E85\u8E91\u8EFB\u8F13\u9087\u914A\u91C9\u923F\u93B0\u9403\u95A8\u95AD\u9730\u9865\u9903\u9945\u9949\u99AD\u99E2\u9A6A\u9D26\u9E1E\u9EDD\u9F2C\u9F72
NGram.KANJI_2_36=\u4E9E\u4F86\u5011\u50B3\u5152\u5169\u5340\u5718\u5B78\u5BE6\u5BF6\u5C07\u5EE3\u61C9\u6230\u6703\u689D\u6A02\u6C23\u7063\u7368\u756B\u7576\u767C\u7A31\u7D93\u7E23\u7E3D\u81FA\u8207\u842C\u85DD\u865F\u8B49\u8B80\u8CFD\u908A\u9435\u95DC\u965D\u9AD4\u9EE8
NGram.KANJI_2_37=\u5480\u5580\u5C39\u67EF\u68B5\u6D85\u8521\u90B1
NGram.KANJI_2_38=\u4E1F\u4F96\u4FE0\u50F1\u5118\u522A\u5291\u52C1\u52DB\u52F3\u52F5\u52F8\u53B2\u55CE\u562F\u580A\u5862\u58AE\u58D8\u58DF\u58E9\u58EF\u5925\u593E\u599D\u5ABD\u5C62\u5EC2\u5EDA\u5EE2\u5F4E\u5F65\u6085\u6158\u61FC\u6200\u62CB\u633E\u6416\u6436\u6490\u64CB\u64E0\u64FA\u6514\u651C\u6524\u6558\u6583\u66B1\u66C6\u66C9\u66E0\u6A11\u6A1E\u6A38\u6A62\u6AB3\u6B16\u6B98\u6BBC\u6C2B\u6DDA\u6DE8\u6DEA\u6DFA\u6EEF\u6EFE\u6F32\u6F51\u6F5B\u700F\u71D2\u7210\u7246\u7260\u72A7\u72F9\u7375\u7378\u758A\u760B\u76DC\u76EA\u77DA\u77FD\u78DA\u7919\u797F\u79AA\u7A05\u7A4C\u7ACA\u7C72\u7D81\u7DDD\u7E31\u7E69\u7E6B\u7E73\u7E96\u7E9C\u81BD\u81C9\u81DF\u8259\u8277\u8396\u83A7\u8523\u8525\u860A\u863F\u8667\u87A2\u87F2\u881F\u883B\u89F8\u8B20\u8B74\u8B9A\u8C4E\u8C6C\u8C93\u8CEC\u8D0A\u8D0F\u8D95\u8E10\u8F4E\u8FAF\u8FF4\u905E\u9072\u9081\u908F\u91AC\u91C0\u91C1\u91D0\u921E\u9223\u9245\u929C\u92B3\u92C1\u9336\u934A\u93C8\u9444\u9452\u947C\u947F\u9592\u95B1\u95C6\u95D6\u95E1\u95E2\u96DE\u9742\u978F\u984F\u9871\u98B1\u98C4\u99ED\u9A37\u9A45\u9A5F\u9AEE\u9B27\u9BCA\u9C77\u9D51\u9D5D\u9E79\u9E7C\u9E7D\u9EB5\u9EBC\u9F61\u9F63\u9F90\u9F9C
NGram.KANJI_3_1=\u5283\u7562\u7DEC\u88E1\u8F2F
NGram.KANJI_3_2=\u5009\u502B\u5049\u5075\u507D\u5091\u5098\u50B5\u50B7\u50BE\u5100\u5104\u511F\u518A\u525B\u5289\u5442\u5805\u589C\u58C7\u5922\u596A\u5A66\u5B6B\u5BE7\u5BE9\u5DBA\u5E63\u5E7E\u5FB9\u6163\u616E\u6176\u61B2\u61B6\u61F8\u639B\u63DA\u63EE\u640D\u64B2\u64C1\u64EC\u6557\u6575\u6607\u66AB\u68C4\u6A39\u6C96\u6CC1\u6E1B\u6E6F\u6E9D\u6EC5\u6F01\u6F64\u6FC3\u7058\u707D\u7344\u7642\u76E4\u7832\u790E\u7B46\u7D05\u7D0B\u7D14\u7D19\u7D1B\u7D39\u7D61\u7DB1\u7DCA\u7DD2\u7DE0\u7DE9\u7DEF\u7DF4\u7E2E\u7E3E\u8105\u8108\u81E8\u8266\u84CB\u84EE\u85A9\u885D\u88DC\u8972\u8A02\u8A0E\u8A13\u8A17\u8A2A\u8A34\u8A3A\u8A3C\u8A69\u8A73\u8A95\u8AA0\u8AA4\u8AB2\u8AC7\u8ACB\u8B00\u8B1B\u8B1D\u8B5C\u8C9D\u8C9E\u8CA2\u8CA8\u8CA9\u8CAB\u8CAC\u8CB7\u8CBF\u8CC0\u8CDE\u8CE2\u8CFC\u8D08\u8DE1\u8E8D\u8ECC\u8EDF\u8EF8\u8F14\u8F1D\u8F2A\u8F44\u9055\u9069\u9077\u907C\u90F5\u91DD\u9285\u92FC\u9326\u932F\u9375\u9396\u93AE\u93E1\u9451\u9589\u95A3\u9663\u9670\u9673\u96BB\u9801\u9802\u9803\u9806\u9808\u9810\u983B\u984D\u9858\u9867\u98EF\u98F2\u98FE\u990A\u99D0\u9A0E\u9A5A\u9B5A\u9CE5\u9DB4\u9E97\u9F8D
NGram.KANJI_3_3=\u543E\u5BEE\u5F18\u6590\u725F\u83C5\u85E9\u9E93
NGram.KANJI_3_4=\u5016\u53AD\u5606\u5629\u58BE\u5F14\u6065\u6144\u646F\u647A\u67F5\u6953\u6C3E\u6F2C\u6F97\u6FB1\u7169\u71E6\u71ED\u74BD\u79BF\u7A1C\u7A4E\u7AAF\u7CDE\u7D17\u7D43\u7E55\u7FA8\u807E\u8139\u8490\u8569\u856A\u87FB\u8A23\u8AB9\u8AE6\u8AFA\u8B2C\u8CD1\u91D8\u92F8\u9318\u96DB\u99B4\u9BC9\u9C2D\u9CF6\u9D61\u9DFA
NGram.KANJI_3_5=\u4E26\u4F75\u4FC2\u500B\u5074\u5099\u512A\u5225\u5247\u5275\u5287\u52D5\u52D9\u52DD\u52E2\u5354\u54E1\u554F\u5712\u57F7\u5831\u5834\u5BAE\u5C0E\u5C64\u5CA1\u5CF6\u5E2B\u5E79\u5EAB\u5F35\u5F37\u5F8C\u5FA9\u611B\u614B\u63A1\u63DB\u6642\u66F8\u6771\u696D\u6975\u69CB\u6A19\u6A4B\u6A5F\u6BBA\u6C7A\u6E2C\u6E96\u6F22\u70BA\u7121\u71B1\u7372\u73FE\u74B0\u7570\u76E3\u78BA\u7A2E\u7A4D\u7AF6\u7BC0\u7BC4\u7BC9\u7C21\u7D00\u7D04\u7D0D\u7D1A\u7D30\u7D42\u7D44\u7D50\u7D66\u7D71\u7DAD\u7DDA\u7DE8\u7E54\u7F85\u7FA9\u7FD2\u8056\u805E\u8077\u8208\u83EF\u8449\u8853\u885B\u88FD\u8907\u898B\u898F\u8996\u89AA\u8A08\u8A18\u8A2D\u8A31\u8A55\u8A5E\u8A66\u8A71\u8A72\u8A8C\u8A8D\u8A9E\u8ABF\u8AD6\u8AF8\u8B58\u8B70\u8B77\u8CA0\u8CA1\u8CB4\u8CBB\u8CC7\u8CEA\u8ECA\u8ECD\u8F03\u8F09\u8F38\u8FB2\u9023\u9031\u9032\u904A\u904B\u904E\u9054\u9060\u9078\u907A\u9084\u9280\u9577\u9580\u958B\u9593\u9678\u967D\u968A\u968E\u969B\u96E2\u96E3\u96F2\u96FB\u97D3\u97FF\u9805\u9818\u982D\u984C\u985E\u98A8\u98DB\u9928\u99AC\u9BAE
NGram.KANJI_3_8=\u5F6B\u6C4E\u7B87\u8A70
NGram.KANJI_3_9=\u540B\u5B5C\u826E
NGram.KANJI_3_11=\u4F83\u4FF8\u51CB\u52BE\u53F1\u548B\u558B\u5CB1\u5D69\u5F3C\u620E\u621F\u64E2\u67DA\u6854\u69CC\u6A35\u6C8C\u6E1A\u6F15\u6FE0\u717D\u7252\u7AFA\u82D3\u83DF\u8431\u9041\u9149\u9798
NGram.KANJI_3_12=\u4ED5\u55E3\u572D\u57A3\u587E\u5983\u5A9B\u5C90\u5E61\u672D\u6960\u6F5F\u72D9\u72E9\u757F\u7949\u7950\u7E82\u7FCC\u82B8\u90B8\u91DC\u961C\u9B45
NGram.KANJI_3_13=\u55AB\u6249\u643E\u6841\u68B1\u725D\u7B8B\u7C95\u7E1E\u7F36\u8A03\u8A6B\u8E74\u95A4
NGram.KANJI_3_15=\u50AD\u50D1\u5132\u51F1\u55AC\u5617\u5687\u584A\u59EA\u5B30\u5BF5\u5C0B\u5C4D\u5EDF\u6182\u61A4\u64AB\u64FE\u66A2\u6897\u694A\u69CD\u6B3D\u6BC0\u6D29\u6F38\u7015\u7149\u71C8\u723A\u7336\u7345\u755D\u76C3\u78A9\u798D\u7AAE\u7DFB\u7E2B\u7F75\u7F77\u81E5\u834A\u852D\u85CD\u8755\u8A3B\u8A54\u8AE7\u8B02\u8B39\u8CAA\u8CE6\u8DA8\u8E5F\u8F5F\u905C\u912D\u919C\u92D2\u932B\u937E\u9418\u9583\u9812\u985B\u9905\u99B3\u99C1\u99D5\u9A30\u9CF3\u9D3B\u9D6C
NGram.KANJI_3_16=\u6D6C\u72FD\u77A5\u8956\u9C0D
NGram.KANJI_3_18=\u5919\u5F4A\u6063\u63AC\u649A\u6715\u6AD3\u71D0\u758B\u834F\u85F7\u88DF\u8F61\u93D1\u98F4\u9D60
NGram.KANJI_3_19=\u4F50\u7DB2\u962A
NGram.KANJI_3_22=\u5E96\u75D4\u91C6
NGram.KANJI_3_23=\u5E9A\u6C40\u821C\u839E\u8FED\u9EDB
NGram.KANJI_3_27=\u5F01\u66DC
NGram.KANJI_3_29=\u5023\u5208\u531D\u536F\u53E9\u54C9\u598A\u59BE\u5A20\u5D6F\u5DF3\u66C7\u66D6\u66F3\u6775\u6A3D\u6ADB\u6B86\u6C72\u6E25\u73EA\u7435\u760D\u7656\u7825\u78D0\u7A14\u7A6B\u7B20\u7BE0\u7CF8\u7DAC\u7DBB\u7DBE\u80E4\u80F4\u837B\u8466\u8568\u867B\u8A63\u91E7\u9320\u935B\u9591\u965B\u98E2\u990C\u9913\u9BAB
NGram.KANJI_3_30=\u60B6\u8AD2\u8CC2\u9237\u9328\u934D\u9397\u9830
NGram.KANJI_3_31=\u4FB6\u50D5\u51CD\u559A\u55AA\u5674\u5857\u585A\u5875\u58B3\u596E\u59E6\u5A41\u5D50\u5E25\u5E33\u5F59\u61C7\u61F2\u6368\u6383\u65AC\u68DF\u68F2\u6A3A\u6B04\u6DBC\u6DF5\u6E26\u6E4A\u6E67\u6F54\u6F70\u6FC1\u6FEB\u7159\u727D\u7652\u77EF\u78EF\u798E\u7A40\u7AAA\u7BE4\u7C60\u7CE7\u7CFE\u7D21\u7D33\u7D5E\u7D79\u7DB4\u7DBF\u7E1B\u7E8F\u7F70\u814E\u816B\u8178\u819A\u84BC\u85A6\u865C\u8766\u8A1F\u8A50\u8A60\u8A6E\u8A87\u8A98\u8AB0\u8ADC\u8AED\u8AEE\u8B0E\u8B19\u8CA7\u8CAF\u8CB8\u8CBC\u8CC3\u8CC4\u8CCA\u8CDC\u8CE0\u8CED\u8ED2\u8F29\u8F3F\u91E3\u920D\u9234\u925B\u9298\u9310\u934B\u958F\u95A5\u9727\u97FB\u9811\u984E\u98FC\u98FD\u99D2\u99FF\u9B31\u9BE8\u9C57\u9CE9\u9CF4\u9D28\u9DF9
NGram.KANJI_3_32=\u4E1E\u502D\u51A5\u5321\u58EC\u5A3C\u5BC5\u5CE8\u61A9\u620A\u65A1\u6714\u6853\u6893\u6C50\u6C5D\u7436\u745A\u745B\u773A\u7941\u7947\u8543\u865E\u8C5A\u914B\u99A8\u9AB8
NGram.KANJI_3_35=\u4E99\u5BA5\u5DFD\u608C\u60C7\u60DA\u6190\u61A7\u6753\u6777\u6787\u6B4E\u6F23\u6FE1\u6FEF\u7337\u7827\u786F\u7893\u7ABA\u7B94\u7BB8\u7C3E\u7D62\u7E6D\u80B1\u81BF\u81C6\u821B\u82E7\u83F0\u84D1\u86ED\u8888\u8B01\u8B04\u8F4D\u9291\u92E4\u932E\u9354\u936C\u939A\u9957\u9AED\u9BAA\u9BAD\u9BD6\u9BDB\u9C3B\u9D1B
NGram.KANJI_3_36=\u50C5\u53E2\u5EE0\u65BC\u70CF\u723E\u7D10\u7D9C\u806F\u8607\u862D\u8A0A\u8AFE\u8CD3\u9019\u9813\u9B6F
NGram.KANJI_3_37=\u4EA8\u4F3D\u5384\u5EFF\u60DF\u66DD\u6E5B\u8087\u82D1\u8FE6\u9640\u9E9F
NGram.KANJI_3_38=\u5147\u525D\u5678\u617E\u6372\u79A6\u8ABC\u92EA\u9438\u9817
NGram.KANJI_4_0=\u6D3C\u718F\u74EE\u8712
NGram.KANJI_4_9=\u4F84\u54C6\u5565\u68F1\u6D82\u83C7
NGram.KANJI_4_10=\u4FE9\u4FED\u51FF\u523D\u5300\u5364\u538C\u5450\u5455\u545C\u54D1\u54D7\u5578\u56A3\u58F6\u592F\u5CE6\u5D2D\u5E90\u6073\u607C\u60EB\u61D2\u62E2\u62E3\u631A\u6320\u6323\u6361\u63B7\u63B8\u63BA\u6405\u65A9\u65F7\u6619\u6655\u67A3\u67E0\u6805\u6808\u6866\u6868\u6869\u6A71\u6BE1\u6C79\u6CA5\u6CDE\u6DA4\u6DA7\u6DA9\u6E85\u70DB\u70E6\u70EB\u7115\u724D\u7410\u759F\u75AE\u75EA\u75F9\u762B\u763E\u76B1\u77EB\u783E\u79C3\u7A8D\u7A9C\u7B5D\u7BF1\u7EC5\u7ED2\u7EDE\u7EE3\u7EF7\u7EF8\u7EFD\u7F00\u7F0E\u7F15\u7F1A\u7F20\u7F24\u7F28\u7FA1\u7FD8\u8038\u803B\u804B\u80AE\u817B\u82C7\u8327\u835E\u8367\u83BA\u8424\u864F\u8681\u8682\u8715\u8717\u8721\u8747\u874E\u8845\u886C\u889C\u88E4\u89C5\u8BB6\u8BB9\u8BC0\u8BC5\u8BE1\u8BEB\u8BEC\u8BF5\u8C0E\u8C1A\u8D2E\u8D31\u8D43\u8D4E\u8D58\u8F67\u8F7F\u9489\u9499\u949D\u94A0\u94A5\u94AE\u94BE\u94D0\u94DB\u94F2\u9508\u950C\u951A\u9525\u952D\u952F\u9530\u953B\u9540\u9550\u9570\u9576\u95F0\u960E\u9668\u96CF\u97E7\u9885\u988A\u98A4\u9965\u9975\u997A\u997F\u9985\u998D\u998F\u9A6E\u9A6F\u9A74\u9A79\u9A7C\u9A82\u9A87\u9CA4\u9CC4\u9CCD\u9CD6\u9E20\u9E25\u9E35\u9E3D\u9E45\u9E49\u9E4A\u9E66
NGram.KANJI_4_16=\u576F\u579B\u6345\u78B4\u79EB\u79F8
NGram.KANJI_4_17=\u4E13\u4E1A\u4E1C\u4E24\u4E25\u4E2A\u4E3E\u4E49\u4E50\u4E66\u4E9A\u4EA7\u4EBF\u4ECE\u4EEC\u4EF7\u4F17\u4F20\u5170\u5173\u519B\u51B3\u51E4\u51FB\u5219\u521B\u522B\u529E\u52A1\u52A8\u52BF\u534F\u5355\u536B\u5386\u53BF\u53D1\u53D8\u542F\u5458\u54CD\u56E2\u56ED\u56F4\u56FE\u573A\u5904\u590D\u5934\u5B81\u5B9E\u5BF9\u5BFC\u5C14\u5C9B\u5E26\u5E7F\u5E94\u5F00\u5F20\u5F3A\u603B\u6218\u65E0\u65F6\u663E\u672F\u6743\u6784\u6807\u6C14\u6C49\u707E\u70ED\u73AF\u73B0\u7535\u76D1\u786E\u79CD\u79EF\u7B80\u7C7B\u7EA2\u7EA6\u7EA7\u7EAA\u7EBF\u7EC4\u7EC7\u7ED3\u7EDF\u7EE7\u7EED\u7EF4\u7F16\u7F57\u804C\u8054\u817E\u8282\u82CF\u83B7\u8425\u89C1\u89C2\u89C4\u89C6\u8BA1\u8BA4\u8BAE\u8BAF\u8BB0\u8BB8\u8BBA\u8BBE\u8BC1\u8BC4\u8BD1\u8BDD\u8BE5\u8BED\u8BF4\u8C03\u8D22\u8D23\u8D28\u8D39\u8D44\u8D5B\u8F66\u8F6C\u8F83\u8FBE\u8FC7\u8FD0\u8FD8\u8FD9\u8FDB\u8FDE\u9009\u94C1\u957F\u95E8\u95EE\u95F4\u95FB\u961F\u9633\u9645\u9646\u96BE\u9879\u9884\u9886\u9898\u98CE\u9A6C\u9F99
NGram.KANJI_4_18=\u51DB\u67B7
NGram.KANJI_4_22=\u4FA5\u545B\u5499\u5520\u5570\u56F1\u5A76\u5C96\u60AF\u60ED\u618B\u61A8\u62A0\u62A1\u62E7\u6363\u6390\u63B0\u6400\u6402\u6512\u6748\u70C1\u732C\u765E\u7663\u76CF\u7741\u781A\u7980\u79C6\u79FD\u7AA5\u7B0B\u7B8D\u7BA9\u7BAB\u7BD3\u7CAA\u7EAB\u7ECA\u7EE2\u7F2D\u7F30\u8110\u8113\u81CA\u835A\u8360\u84D6\u852B\u87E5\u8869\u8A8A\u8BA5\u8BF2\u8C05\u8C12\u8D30\u8D4A\u8D61\u8DF7\u8E6D\u8E8F\u8F95\u8F99\u8FAB\u94B3\u94C6\u94E3\u9504\u954A\u9563\u95FA\u9893\u9981\u9992\u9AA1\u9CAB\u9E2F\u9E33\u9EB8
NGram.KANJI_4_24=\u4E22\u4E8F\u4F1E\u4FA3\u5151\u517D\u51BB\u51D1\u5220\u529D\u52CB\u5367\u5389\u5395\u53E0\u53F9\u5413\u548F\u5524\u575E\u575F\u5784\u5792\u57A6\u57AB\u58F3\u5986\u5988\u5A04\u5A07\u5BA0\u5C18\u5C82\u5DE9\u5E10\u5E1C\u5F2F\u60E9\u6124\u629B\u6321\u6324\u635E\u63FD\u6401\u644A\u6491\u655B\u658B\u6635\u67AB\u67DC\u680B\u692D\u6984\u6A31\u6B7C\u6BD9\u6C22\u6CA6\u6CA7\u6CEA\u6CFB\u6CFC\u6D46\u6D47\u6D4A\u6D51\u6DA1\u6E0A\u6E83\u6EE4\u6EE5\u6F9C\u6FD2\u70C2\u7237\u727A\u730E\u7574\u75AF\u7792\u7816\u7845\u78B1\u7A77\u7A91\u7A9D\u7AD6\u7B3C\u7B5B\u7CAE\u7EA4\u7EB1\u7EBA\u7ECE\u7ED1\u7EF0\u7EF3\u7F14\u7F1D\u7F34\u7F62\u8042\u806A\u80A0\u80A4\u80BE\u80BF\u80C0\u810F\u8138\u8231\u8270\u829C\u82CD\u8350\u83B9\u841D\u8574\u8680\u8BB3\u8BBC\u8BBD\u8BC8\u8BF1\u8BFD\u8C0A\u8C0D\u8C1C\u8C24\u8C26\u8C2C\u8C2D\u8C34\u8D1E\u8D2C\u8D3C\u8D41\u8D42\u8D4C\u8D50\u8D5A\u8F69\u8F88\u8F90\u8FA9\u915D\u9171\u9493\u949E\u94A7\u94A9\u94BB\u94C3\u94C5\u94DD\u94F8\u9505\u9510\u9523\u9524\u95EF\u95F7\u95F9\u9600\u9610\u96F3\u97F5\u987D\u9882\u9888\u9896\u98D8\u9971\u9972\u9976\u997C\u9A84\u9A86\u9A8F\u9A97\u9A9A\u9AA4\u9CB8\u9CDE\u9E26\u9E43\u9E64\u9E70\u9F7F\u9F9F
NGram.KANJI_4_28=\u534E\u62A5\u7ECF\u7F51
NGram.KANJI_4_34=\u4E34\u4E3D\u4E4C\u4E54\u4E60\u4E61\u4E70\u4EB2\u4EC5\u4EEA\u4F18\u4F1F\u4F24\u4F26\u4FA7\u50A8\u513F\u5174\u517B\u518C\u519C\u51B5\u51CF\u5218\u521A\u5267\u52B3\u5356\u5382\u5385\u538B\u53A6\u5434\u5706\u5723\u5757\u575A\u575B\u575D\u5907\u591F\u593A\u5956\u5B59\u5BA1\u5BAB\u5BBD\u5BBE\u5BFB\u5C42\u5C81\u5E01\u5E08\u5E86\u5E93\u5F02\u5F39\u5F52\u5F55\u5F7B\u6000\u6001\u6076\u620F\u6237\u6267\u6269\u626C\u62A2\u62A4\u62DF\u62E5\u62E9\u6325\u635F\u6362\u6444\u6653\u6682\u6740\u6742\u6768\u6781\u6811\u6837\u6865\u68C0\u6B22\u6BC1\u6BD5\u6C47\u6C9F\u6CAA\u6CFD\u6D4B\u6DA8\u6E10\u6EE1\u6EE8\u706D\u7075\u70DF\u7231\u739B\u7597\u76D6\u76D8\u77FF\u7801\u7840\u79BB\u7A33\u7ADE\u7B14\u7B7E\u7CA4\u7D27\u7EB3\u7EBD\u7EC3\u7EC6\u7EC8\u7ECD\u7ED5\u7ED9\u7EDC\u7EDD\u7EE9\u7EFC\u7EFF\u7F13\u7F29\u8083\u80DC\u8111\u814A\u8230\u827A\u8363\u836F\u8428\u84DD\u867D\u8865\u88AD\u89C8\u8BA2\u8BA8\u8BA9\u8BAD\u8BB2\u8BBF\u8BC6\u8BCD\u8BD5\u8BEF\u8BF7\u8BF8\u8BFA\u8BFB\u8C08\u8D1D\u8D1F\u8D21\u8D25\u8D27\u8D2D\u8D2F\u8D35\u8D38\u8DC3\u8F6E\u8F6F\u8F7B\u8F7D\u8F86\u8F91\u8F93\u8F96\u8FB9\u8FBD\u8FC1\u8FDC\u8FDD\u9002\u9057\u90BB\u90D1\u91CA\u9488\u949F\u94A2\u94B1\u94F6\u9500\u9526\u9547\u9614\u9634\u9635\u9636\u9648\u9655\u9669\u9690\u97E9\u9875\u9876\u987A\u987B\u987E\u987F\u9891\u989D\u98DE\u9986\u9A7B\u9A8C\u9C81\u9C9C\u9F50
NGram.KANJI_4_39=\u4E1B\u4E1D\u4E27\u4EA9\u4ED1\u4ED3\u4F2A\u4FA6\u4FA8\u503A\u503E\u507F\u5188\u51AF\u51C0\u51C9\u51ED\u51EF\u5242\u5251\u52B2\u5362\u53A2\u5415\u5417\u5428\u55B7\u5760\u5899\u5939\u594B\u5987\u5A31\u5A74\u5BAA\u5C1D\u5C7F\u5C97\u5CAD\u5E05\u5E2E\u5E99\u5E9E\u5E9F\u5F03\u5FC6\u5FE7\u60AC\u60CA\u60EF\u626B\u6270\u629A\u62E6\u62E8\u6446\u6447\u654C\u67AA\u680F\u6863\u68A6\u6C64\u6D01\u6D53\u6D9D\u6DA6\u6E14\u6E17\u6EDA\u6EE9\u707F\u70BC\u70E7\u7275\u72B9\u72EE\u72F1\u743C\u7545\u76D0\u7855\u7978\u7B79\u7BEE\u7EA0\u7EAC\u7EAF\u7EB2\u7EB5\u7EB7\u7EB8\u7EB9\u7ED8\u7EEA\u7EF5\u7F05\u7F06\u7F18\u7F5A\u80C1\u80F6\u8109\u8206\u8273\u82F9\u8346\u8361\u83B2\u8427\u8651\u867E\u8854\u89C9\u8BC9\u8BCA\u8BD7\u8BDA\u8BDE\u8BE2\u8BE6\u8BFE\u8C01\u8C0B\u8C10\u8C13\u8C22\u8C23\u8C28\u8C31\u8D24\u8D26\u8D29\u8D2A\u8D2B\u8D34\u8D37\u8D3A\u8D3E\u8D3F\u8D4B\u8D4F\u8D54\u8D56\u8D5E\u8D60\u8D62\u8D75\u8D76\u8D8B\u8F68\u8F70\u8F74\u8F85\u8F89\u8FC8\u8FDF\u900A\u9012\u903B\u9093\u90AE\u917F\u9274\u94A6\u94DC\u94ED\u94FA\u94FE\u9501\u950B\u9519\u9521\u952E\u955C\u95EA\u95ED\u95F2\u95F8\u95FD\u9601\u9605\u9647\u96B6\u96FE\u9877\u9881\u9887\u9897\u989C\u98A0\u996D\u996E\u9970\u9A70\u9A71\u9A73\u9A76\u9A7E\u9A91\u9C7C\u9E1F\u9E21\u9E23\u9E2D\u9E3F\u9E4F\u9F84
NGram.KANJI_5_10=\u5239\u8EAF
NGram.KANJI_5_11=\u51C4\u8471
NGram.KANJI_5_12=\u6DC0\u7C98
NGram.KANJI_5_13=\u5631\u5815\u8695
NGram.KANJI_5_14=\u4E71\u4FA0\u5265\u52B1\u5374\u53A8\u53D9\u58EE\u5BDD\u5BFF\u5C3D\u5C4A\u5CE1\u5F25\u5F84\u604B\u60A6\u60E7\u60E8\u631F\u636E\u643A\u663C\u664B\u67A2\u6816\u697C\u6B8B\u6BB4\u6D45\u6E7F\u6EDE\u6F5C\u706F\u7089\u72ED\u732A\u732B\u76D7\u793C\u7977\u7A0E\u7A83\u80C6\u811A\u8131\u82A6\u830E\u848B\u865A\u866B\u86EE\u89E6\u8A89\u8DF5\u8E0A\u8E2A\u8F9E\u9065\u968F\u9759\u9EA6
NGram.KANJI_5_18=\u601C\u75D2
NGram.KANJI_5_26=\u4E07\u4E0E\u4E89\u4F1A\u4F53\u515A\u5185\u5199\u533A\u533B\u53C2\u53CC\u53F7\u58F0\u5965\u5B66\u5B9D\u5C06\u5C5E\u5F53\u62C5\u6570\u65AD\u65E7\u6761\u6765\u6A2A\u6B27\u6CA1\u6E29\u6E7E\u70B9\u72B6\u72EC\u732E\u753B\u79F0\u88C5\u9EC4
NGram.KANJI_5_29=\u693F\u82EB
NGram.KANJI_5_34=\u53F6\u6D9B\u83B1
NGram.KANJI_5_39=\u5C61\u788D
NGram.KANJI_6_0=\u4E10\u4E52\u4EC6\u4F88\u4FD0\u51F3\u533E\u53ED\u53EE\u5406\u541D\u5429\u5435\u5440\u5490\u5495\u54B1\u54C4\u54FC\u557C\u55D3\u5669\u56E4\u5777\u5992\u59E8\u5B7D\u5BDE\u5BE5\u5C79\u5C94\u5DCD\u5E18\u5E1A\u5E54\u5FF1\u604D\u6064\u60F6\u6127\u6177\u6233\u6252\u625B\u6273\u6296\u62C2\u62C7\u62F4\u638F\u6396\u63E3\u63EA\u6413\u6479\u64A9\u64C2\u659F\u667E\u6760\u6845\u6963\u6A90\u6B83\u6C13\u6C5E\u6D8E\u6D95\u6DCC\u6ED4\u6F13\u6F3E\u6FA1\u7076\u70D8\u710A\u71CE\u7239\u72E1\u73B7\u7599\u759A\u75A4\u75CA\u7629\u7682\u76C5\u76EF\u778E\u77AA\u787C\u7889\u788C\u78BE\u79E7\u7A96\u7A98\u7B77\u7C7D\u7CB1\u7D0A\u7D6E\u7F94\u7FCE\u8116\u814B\u814C\u819B\u828D\u82DF\u8301\u83E0\u85D5\u8611\u86A3\u8708\u8822\u8C4C\u8DB4\u8DEA\u8E42\u8E66\u8E72\u8EBA\u901B\u9157\u970E\u97ED
NGram.KANJI_6_3=\u62FC\u88D4\u9B4F
NGram.KANJI_6_9=\u4ED7\u4F63\u4FCF\u5018\u50BB\u50F5\u5154\u5201\u522E\u5254\u527F\u5306\u5462\u5492\u5496\u54A8\u54AA\u554A\u5561\u5564\u5566\u5885\u5938\u5AC2\u5AE9\u5CED\u5F64\u6084\u608D\u60A8\u60D5\u61C2\u61C8\u6254\u626F\u62AC\u6346\u634D\u640F\u6454\u6487\u6495\u64D2\u6746\u6789\u68B3\u68F5\u695E\u6986\u6995\u69A8\u6A44\u6AAC\u6B79\u6C28\u6C2E\u6CF5\u6DE4\u6E34\u6E3A\u6E89\u6F29\u70AB\u70AC\u7130\u715E\u7184\u71AC\u7238\u7281\u72E0\u74E3\u74F7\u7529\u7578\u761F\u7626\u76D4\u775B\u7779\u7784\u77BB\u780C\u780D\u7838\u7898\u78C5\u78F7\u7AED\u7B28\u7BE1\u7C07\u7CD5\u7CD9\u7CEF\u7F38\u800D\u8084\u809A\u8165\u816E\u832B\u8334\u840D\u8774\u886B\u888D\u88D9\u88F9\u8C41\u8D81\u8D9F\u8E22\u8E29\u8EB2\u8F9C\u9165\u918B\u9631\u964B\u964C\u9661\u9709\u9739\u9776\u9AD3\u9ED4
NGram.KANJI_6_10=\u4E53\u5582\u5600\u6342\u7B06
NGram.KANJI_6_11=\u5288\u543C\u5475\u5486\u54EE\u5598\u56BC\u5962\u5A36\u5A9A\u5B75\u5BA6\u5C38\u5C4E\u5F8A\u5F98\u627C\u62CC\u62D7\u63C9\u6930\u6954\u69D0\u6BEF\u6C90\u6CBD\u6CBE\u6F31\u6F88\u70D9\u7329\u75BC\u75F0\u7737\u77D7\u7B19\u7FB9\u803F\u80D6\u813E\u81C0\u8205\u8309\u83BD\u846B\u8517\u868C\u8759\u8815\u8859\u8B6C\u8E81\u8EAC\u90A2\u9698\u9B44
NGram.KANJI_6_12=\u722C\u7FD4
NGram.KANJI_6_16=\u5228\u5315\u542E\u54CE\u5509\u5527\u5543\u55B3\u55E1\u5636\u568E\u5FFF\u61E6\u6376\u642A\u6726\u74E4\u76F9\u7736\u7BD9\u8019\u80F0\u80F3\u812F\u818A\u8200\u8214\u8638\u869C\u86C0\u86C6\u86D4\u87C6\u88B1\u8902\u8C7A\u8E4B\u9119
NGram.KANJI_6_18=\u67D2\u6ED3\u87C0\u87CB\u8DDB\u901E\u9163
NGram.KANJI_6_20=\u4F5B\u52D2\u54C8\u62FF\u66FC\u6D59\u704C\u7586\u9ECE
NGram.KANJI_6_21=\u4E48\u4EFF\u4F19\u4FF1\u5021\u5077\u5195\u5212\u5269\u5401\u541E\u5427\u54EA\u5587\u558A\u55BB\u566A\u573E\u574E\u5783\u57AE\u584C\u58E4\u5960\u5976\u59CA\u5A1C\u5DE2\u5F99\u600E\u6015\u6263\u626D\u6293\u62C6\u62D6\u62EF\u62F1\u6316\u632A\u6380\u6389\u63D2\u641E\u64C5\u64CE\u65F1\u6664\u6735\u6770\u67EC\u6846\u684C\u68AD\u6B47\u6B49\u6B67\u6C1B\u6C27\u6C2F\u6C5B\u6C89\u6DF9\u6EAF\u70AE\u70E4\u731C\u7334\u73BB\u7470\u76FC\u788E\u789F\u78B0\u78B3\u7A0D\u7A3B\u7A57\u7CB9\u7F69\u8335\u8354\u84BF\u8DCC\u8DD1\u904F\u90A8\u9189\u9677\u9738\u978B
NGram.KANJI_6_22=\u5162\u53E8\u542D\u5501\u552C\u5639\u563F\u56B7\u6043\u60B4\u6194\u61CA\u634E\u63CD\u6414\u64AC\u6DAE\u6E43\u6F66\u7095\u7316\u733E\u7728\u7830\u78D5\u7ABF\u7FE9\u8018\u80EF\u8198\u8693\u86AA\u86AF\u874C\u8783\u879F\u8892\u8E6C
NGram.KANJI_6_23=\u4FD8\u4FEF\u501A\u5085\u5180\u526A\u5323\u54ED\u5634\u56CA\u58A9\u58F9\u5955\u5978\u59DA\u5A49\u5B55\u5BC7\u5BE8\u5D4C\u5E62\u6467\u64BC\u6500\u655E\u6572\u658C\u6670\u68CD\u68D5\u68E0\u6912\u6A0A\u6BB7\u6C9B\u6D3D\u6DC6\u6E23\u6F8E\u7011\u7092\u714C\u73AB\u7405\u7624\u76D2\u7960\u79C9\u7A20\u7BF7\u7F50\u804A\u8086\u81C2\u8292\u82DE\u852C\u857E\u859B\u8760\u8C6B\u8DBE\u8E48\u8F9F\u96A7
NGram.KANJI_6_25=\u4E8E\u5DF2\u5FB7\u7AD9
NGram.KANJI_6_28=\u4E58\u4ECD\u4EFD\u4F30\u4F60\u4F69\u503C\u5047\u51B0\u51F0\u5361\u5377\u53E6\u54E5\u552E\u5708\u5740\u5761\u57C3\u5821\u589E\u5979\u59C6\u5B69\u5B83\u5E15\u5E76\u5F17\u5F88\u6208\u622A\u624E\u627E\u62D4\u62DC\u63ED\u641C\u6536\u6548\u65C1\u665A\u6668\u67E5\u6B65\u6BCF\u6C61\u6CDB\u6D4E\u6D89\u6DB5\u6E38\u6EAA\u6FB3\u70B8\u745F\u7538\u7A97\u7F3A\u7F55\u805A\u8258\u827E\u82AC\u8303\u83F2\u8482\u85CF\u8DDF\u903E\u9080\u970D\u9760\u9ED1\u9ED8
NGram.KANJI_6_29=\u634F\u6518\u7B50\u809B
NGram.KANJI_6_30=\u54A7\u57C2\u5AB3\u60CB\u6886\u8378\u85D0\u8671
NGram.KANJI_6_32=\u5080\u5121\u51A4\u54AC\u55DC\u592D\u5DEB\u6292\u68D8\u69B4\u6A59\u6E24\u7FC5\u80DA\u8180\u86DB\u8700\u8DCB\u9761
NGram.KANJI_6_34=\u4E30\u51E0\u542C\u613F
NGram.KANJI_6_35=\u4E56\u547B\u55FD\u5C41\u606C\u6115\u6CAE\u7119\u795F\u7CDC\u86C9\u86F9\u8713\u873B\u8757\u8925\u892A\u96F9
NGram.KANJI_6_37=\u51B2\u5308\u5398\u54B8\u59DC\u5C4F\u5D14\u5F6D\u60E0\u6241\u6350\u699C\u6BEB\u6C6A\u6CC4\u6DEE\u6F58\u6F6D\u7199\u77EE\u7ADF\u8058\u820D\u8212\u8389\u8587\u884D\u8881\u8FA8\u8FF9\u96D5
NGram.KANJI_6_39=\u574F\u6251\u6302
NGram.KANJI_7_0=\u52FA\u5544\u60F0\u6994\u86A4\u86E4
NGram.KANJI_7_3=\u4E59\u4E7E\u4EAD\u4EF0\u4EF2\u4F0F\u4F10\u4FAF\u4FCA\u500D\u501F\u5076\u508D\u50E7\u5112\u5146\u5192\u51AC\u51DD\u51FD\u5200\u5237\u524A\u52A3\u52C3\u52C7\u52DF\u5351\u5352\u5353\u5378\u537F\u53E5\u5439\u54FA\u574A\u5782\u57CB\u5893\u58C1\u5915\u5937\u5949\u5951\u5974\u59B9\u5A18\u5A5A\u5ACC\u5B54\u5B5D\u5B64\u5B8F\u5BBF\u5BD2\u5C3A\u5C6F\u5CB3\u5D07\u5DE7\u5E84\u5E8A\u5F26\u5F69\u5F70\u5F90\u5FAA\u5FCD\u6012\u6016\u602A\u60A0\u60B2\u60BC\u6148\u6162\u6170\u6291\u6298\u62AB\u62BC\u62BD\u62D2\u62D3\u62D8\u62F3\u6311\u638C\u6398\u63E1\u642C\u6458\u64A4\u654F\u656C\u659C\u65E2\u65E8\u65EC\u6606\u6614\u6676\u6691\u6696\u66F9\u6749\u676F\u679A\u679D\u67CF\u67D4\u67F1\u67F3\u67F4\u6817\u6842\u6843\u6851\u68A8\u68CB\u68D2\u6B20\u6B32\u6BBF\u6C57\u6C88\u6CCA\u6D17\u6D1E\u6D69\u6D6E\u6D78\u6DE1\u6DFB\u6E58\u6EB6\u6F0F\u6F20\u7070\u708E\u70AD\u7126\u718A\u71C3\u7267\u72C2\u731B\u7384\u73A9\u73CD\u7434\u75AB\u75DB\u76C6\u76FE\u773C\u7891\u78C1\u795D\u7965\u79D2\u79DF\u79E6\u7A00\u7B11\u7B51\u7B54\u7C89\u7C92\u7CD6\u7D2B\u7F8A\u7FBD\u7FFC\u8010\u80A5\u80CE\u8150\u8179\u819C\u8247\u829D\u82B3\u82D7\u82E6\u8302\u8336\u8352\u83CA\u83CC\u83DC\u845B\u846C\u84B2\u84B8\u84C4\u8584\u864E\u86C7\u8861\u8863\u8870\u888B\u8896\u88D5\u8986\u8C46\u8DA3\u8E0F\u8F9B\u8FC5\u8FEB\u8FF7\u9003\u9006\u902E\u9042\u9063\u90ED\u963B\u9676\u96EA\u9756\u9B3C\u9B42\u9F3B
NGram.KANJI_7_6=\u4E01\u4E03\u4E45\u4E5D\u4E88\u4E92\u4EA1\u4ECB\u4EE4\u4F01\u4F0A\u4F2F\u4F3C\u4F4E\u4F4F\u4F55\u4F8B\u4F9D\u4FBF\u4FEE\u505C\u50CF\u516B\u516D\u5175\u5177\u5178\u5207\u520A\u5224\u526F\u529F\u52A9\u5343\u5348\u535A\u5370\u53BB\u53CB\u53F3\u5409\u542B\u544A\u547C\u5584\u5747\u5802\u590F\u592B\u5931\u5947\u597D\u5A01\u5A92\u5B63\u5B8C\u5B97\u5BA2\u5BA3\u5BA4\u5BB3\u5BB9\u5BC6\u5BCC\u5BDF\u5C04\u5C1A\u5C45\u5C4B\u5CB8\u5DE6\u5E0C\u5E1D\u5E2D\u5E55\u5E8F\u5E95\u5E97\u5EA7\u5EB7\u5EF6\u5F8B\u5FAE\u5FC5\u5FD7\u5FF5\u601D\u6025\u606F\u60F3\u611F\u623F\u6253\u6279\u627F\u6295\u6297\u62EC\u6388\u6392\u63F4\u6545\u6551\u6574\u6599\u65C5\u65E9\u6613\u6620\u6625\u666E\u666F\u66B4\u66F4\u670D\u671B\u6728\u672B\u6751\u677E\u67B6\u6838\u6839\u6848\u68EE\u690D\u6982\u6A21\u6B4C\u6B62\u6B66\u6BB5\u6BCD\u6C0F\u6C38\u6C42\u6CBF\u6CE2\u6CE8\u6D0B\u6D3E\u6D88\u6DF1\u6E05\u6E56\u706B\u7167\u7206\u7236\u7247\u7387\u7530\u7537\u7559\u7565\u7591\u75C5\u767B\u767D\u767E\u7687\u76DB\u76DF\u771F\u7763\u77ED\u7834\u79FB\u7A81\u7AE0\u7AEF\u7B56\u7B97\u7C4D\u7CBE\u7D20\u7D22\u7F72\u7FA4\u8001\u8003\u81F4\u822A\u826F\u82B1\u8349\u843D\u878D\u8857\u89D2\u8B66\u8C37\u8D70\u8D85\u8D8A\u8DB3\u8FF0\u8FFD\u9001\u901F\u90A3\u90A6\u914D\u91CE\u9632\u963F\u9644\u964D\u9664\u96C4\u96E8\u9752\u9769\u98DF
NGram.KANJI_7_7=\u4E09\u4E0A\u4E0B\u4E0D\u4E16\u4E3B\u4E8B\u4E8C\u4EE3\u4EE5\u4F4D\u4F5C\u4F7F\u5165\u5168\u516C\u5171\u51FA\u5206\u5229\u5236\u524D\u529B\u52A0\u5316\u5317\u5357\u539F\u53CA\u53F0\u5408\u540C\u540D\u548C\u5730\u57FA\u5916\u591A\u5929\u5B50\u5B9A\u5BB6\u5C0F\u5C71\u5DDE\u5DE5\u5E02\u5E73\u5EA6\u5EFA\u5F0F\u6027\u6210\u6240\u6307\u653F\u6587\u65B0\u65B9\u660E\u6700\u6709\u671F\u672C\u6B21\u6B63\u6C11\u6CBB\u6CD5\u6D77\u7269\u7279\u7406\u751F\u7528\u7531\u754C\u76EE\u76F8\u793E\u79D1\u7ACB\u7B2C\u7B49\u7CFB\u8005\u80FD\u81EA\u82F1\u884C\u8868\u897F\u8981\u901A\u9053\u90E8\u90FD\u91CD\u9AD8
NGram.KANJI_7_9=\u4E4D\u4F36\u5319\u6A61\u6DCB\u7194
NGram.KANJI_7_11=\u4E5E\u4F43\u5026\u50FB\u515C\u5243\u5420\u5446\u54B3\u54BD\u553E\u55A7\u5703\u5984\u5AC9\u5B09\u5C51\u5DFE\u5ED3\u5F1B\u6055\u618E\u62D9\u65A7\u6652\u6977\u6EBA\u707C\u75D8\u79E4\u7AFF\u7B4F\u7CA5\u808B\u8098\u80B4\u8235\u82DB\u849C\u8549\u868A\u86FE\u8718\u914C
NGram.KANJI_7_12=\u4E08\u4E38\u4F8D\u50DA\u5203\u5256\u52C9\u52D8\u52FE\u5320\u533F\u5375\u53D4\u540F\u54E8\u56DA\u5806\u5996\u5999\u59A5\u59A8\u59FF\u5AE1\u5BB0\u5BF8\u5C09\u5C3F\u5C48\u5C65\u5D29\u5E06\u5E4C\u5EB5\u5EB6\u5EB8\u5F13\u5FCC\u5FD8\u6052\u606D\u609F\u60D1\u614E\u6247\u62B1\u6349\u64E6\u6577\u65ED\u6674\u6734\u67C4\u6850\u690E\u6A58\u6B3A\u6B89\u6C41\u6CBC\u6CCC\u6CF3\u6D74\u6DAF\u6DF3\u6ECB\u6F02\u6F84\u71E5\u7261\u7272\u72AC\u72FC\u733F\u7409\u755C\u76F2\u7720\u77AC\u77E2\u7802\u786B\u78E8\u7901\u7948\u79E9\u7A1A\u7A74\u7AE3\u7B4B\u7B52\u7BB1\u7C3F\u8015\u8096\u809D\u80A2\u80A9\u80AA\u80BA\u80F8\u8102\u810A\u8154\u8155\u8170\u817A\u81A8\u81ED\u820C\u8236\u82BD\u8305\u83E9\u83F1\u840C\u85FB\u8650\u8702\u8A93\u8E44\u8FB0\u9038\u9091\u90AA\u916C\u9175\u9177\u9685\u96C0\u96C7\u96CC\u97AD
NGram.KANJI_7_13=\u63D6\u803D
NGram.KANJI_7_16=\u602F\u7566
NGram.KANJI_7_18=\u634C\u7C38
NGram.KANJI_7_19=\u4E18\u4E73\u4E95\u4EAB\u4EC1\u4ED8\u4ED9\u4F11\u4F34\u4F38\u4F59\u4FB5\u4FC3\u4FD7\u5012\u5019\u5065\u50AC\u5144\u5145\u514D\u517C\u51A0\u51B7\u5211\u5238\u523A\u523B\u5272\u52E4\u5360\u5371\u539A\u541B\u5426\u5438\u5473\u54F2\u5510\u552F\u5531\u559C\u5609\u56F0\u56FA\u591C\u5948\u594F\u59BB\u59D3\u5B85\u5B87\u5B88\u5B99\u5B9C\u5BC4\u5BFA\u5C0A\u5C3E\u5CA9\u5D0E\u5DE1\u5DE8\u5DEE\u5DF1\u5E45\u5E78\u5E7B\u5E7C\u5EAD\u5EF7\u5F1F\u5F31\u5F79\u5F7C\u5F85\u5F92\u5FA1\u5FE0\u6050\u60A3\u6212\u62DB\u632F\u6355\u63A2\u63AA\u63CF\u642D\u6469\u64CD\u653B\u6563\u660C\u662D\u667A\u6697\u66FF\u6750\u675F\u677F\u6790\u67D3\u682A\u6885\u68B0\u6B8A\u6B96\u6BDB\u6C60\u6CB9\u6CC9\u6D25\u6D66\u6DB2\u6DF7\u6E21\u6ED1\u6F2B\u6F6E\u6FC0\u7235\u725B\u72AF\u7389\u7532\u7533\u756A\u75BE\u75C7\u76AE\u76CA\u7740\u786C\u7956\u7968\u796D\u7981\u79C0\u79C1\u79CB\u79D8\u7A3F\u7AE5\u7AF9\u7E41\u7F6A\u7FFB\u8089\u80CC\u80DE\u81E3\u821E\u8239\u82E5\u8328\u8377\u85E4\u8840\u88C1\u88C2\u8C6A\u8D64\u8DDD\u8FCE\u8FD4\u9000\u9014\u907F\u90CA\u90CE\u90E1\u9152\u9178\u9686\u9694\u969C\u9707\u9732\u9AA8\u9B54\u9E7F\u9EBB
NGram.KANJI_7_20=\u4E39\u4E43\u4EAE\u4F73\u504F\u505A\u51C6\u51CC\u52AA\u5339\u5347\u53EB\u53EC\u5448\u5766\u57F9\u5854\u585E\u58A8\u5B8B\u5C01\u5CF0\u5E72\u5EC9\u5F80\u5F81\u5FBD\u5FEB\u6069\u6211\u624D\u628A\u62B5\u62CD\u6309\u63A7\u64AD\u6566\u6597\u65CB\u65D7\u6628\u6717\u6731\u674E\u675C\u683D\u6881\u6B3E\u6BD2\u6C7D\u6C99\u6CE5\u6CF0\u6D1B\u6D2A\u70C8\u719F\u724C\u7259\u73E0\u73ED\u745E\u74E6\u7518\u751A\u7686\u770B\u7B26\u8033\u80A1\u80E1\u821F\u83AB\u8499\u8D74\u8DE8\u900F\u9010\u9047\u904D\u906D\u9675\u96C5\u96F6\u96F7\u9700\u9F13
NGram.KANJI_7_21=\u5764\u59D0\u5A03\u6062\u6108\u68C9\u7164\u79BE\u7BAD\u903C
NGram.KANJI_7_23=\u4EA5\u50B2\u532A\u5366\u543B\u54E9\u5632\u59D1\u5BB5\u5DF7\u5F6A\u5F6C\u5FFD\u6070\u6168\u61BE\u63A0\u63A9\u6478\u65A4\u68A7\u6A1F\u6CAB\u70F9\u711A\u723D\u7262\u72F8\u751C\u754F\u75B9\u76C8\u7709\u7897\u7CCA\u7F9E\u8299\u82AD\u82B9\u82D4\u8304\u84C9\u84EC\u854A\u85AF\u86D9\u8FA3\u9187\u97A0
NGram.KANJI_7_25=\u4E14\u4E5F\u4F46\u514B\u5176\u5230\u5373\u53EA\u540E\u5982\u5C3C\u5DF4\u6216\u62C9\u65AF\u66FE\u6B64\u6D32\u6D6A\u7BC7\u800C
NGram.KANJI_7_28=\u4E4E\u4E9B\u4EA6\u4EC0\u4FC4\u5403\u5957\u5C24\u6089\u6258\u67D0\u758F\u7FF0\u8D6B
NGram.KANJI_7_29=\u4FAE\u5944\u5A29\u6101\u62ED\u6328\u637B\u6666\u6687\u66AE\u673D\u6756\u67FF\u6813\u68A2\u699B\u7078\u708A\u7396\u7422\u7525\u75E2\u76BF\u7766\u77B3\u7A3C\u7A92\u819D\u81FC\u8237\u8338\u8511\u88F3\u8FC2
NGram.KANJI_7_32=\u4E11\u4F3A\u4F51\u5197\u51B6\u51F9\u52FF\u541F\u5507\u5589\u5993\u5A7F\u5AC1\u5B9B\u5BC2\u5BE1\u5F04\u5F0A\u5F27\u6020\u6028\u6068\u6094\u6109\u611A\u614C\u621A\u62B9\u62D0\u62F7\u62FE\u632B\u633D\u6367\u660F\u6627\u6643\u66D9\u674F\u6795\u67AF\u67D1\u6876\u68DA\u68FA\u6905\u69FD\u6A80\u6B6A\u6CB8\u6CE3\u6DD1\u6DEB\u6E9C\u6EA2\u6EF4\u6F06\u714E\u716E\u722A\u7280\u74A7\u752B\u75B2\u75D5\u75F4\u77AD\u77E9\u785D\u79BD\u7A3D\u7A9F\u7B1B\u7B95\u7C9F\u7CDF\u80C3\u8106\u817F\u818F\u81B3\u828B\u82A5\u82AF\u840E\u851A\u853D\u8776\u87F9\u8877\u8910\u8912\u8C79\u8D66\u8FB1\u9017\u90C1\u916A\u9699\u96C1\u971C\u9774\u978D
NGram.KANJI_7_33=\u4E4B\u4E86\u4E94\u4EA4\u4EAC\u4ECA\u4ED6\u4EF6\u4EFB\u4F9B\u4FDD\u4FE1\u5143\u5148\u5149\u518D\u5217\u521D\u5305\u5341\u534A\u53C8\u53CD\u53D6\u53D7\u53E3\u53E4\u53EF\u53F2\u53F8\u5404\u5411\u5468\u547D\u54C1\u5546\u5668\u56DB\u56DE\u56E0\u571F\u578B\u57CE\u57DF\u5883\u58EB\u592A\u592E\u5973\u59CB\u59D4\u5B57\u5B58\u5B89\u5B98\u5C11\u5C31\u5C40\u5C55\u5DDD\u5E03\u5E38\u5E9C\u5F15\u5F62\u5F71\u5F97\u5FC3\u60C5\u610F\u624B\u6280\u6301\u63A5\u63A8\u63D0\u652F\u6539\u653E\u6559\u65BD\u65CF\u661F\u66F2\u671D\u672A\u6797\u679C\u6821\u683C\u6B7B\u6BD4\u6C34\u6C5F\u6CB3\u6D3B\u6D41\u6E2F\u6E90\u6F14\u7136\u7248\u738B\u7403\u76F4\u7701\u77E5\u77F3\u7814\u793A\u795E\u798F\u7A0B\u7A76\u7A7A\u7BA1\u7C73\u7F6E\u7F8E\u80B2\u81F3\u822C\u8272\u8457\u88AB\u89E3\u8A00\u8C61\u8D77\u8DEF\u8EAB\u8FD1\u9020\u91CC\u91CF\u91D1\u9650\u9662\u96C6\u975E\u9762\u97F3\u9996\u9999
NGram.KANJI_7_35=\u55C5\u57A2\u58D5\u59E5\u637A\u74E2\u7CE0\u895F
NGram.KANJI_7_37=\u4E19\u4E32\u4E4F\u4E91\u4EC7\u4ED4\u4F0D\u5141\u51E1\u51F6\u51F8\u52AB\u535C\u53C9\u53DB\u540A\u5410\u54C0\u559D\u5750\u5751\u576A\u57E0\u5824\u582A\u5830\u5835\u5851\u5858\u586B\u5954\u59FB\u5A46\u5B5F\u5BB4\u5BD3\u5C16\u5C60\u5CFB\u5D16\u5E16\u5E3D\u5E7D\u5E87\u5ECA\u5FD9\u60DC\u60F9\u6155\u6167\u6234\u626E\u6276\u6284\u633A\u6377\u6492\u649E\u64B0\u6562\u6591\u65A5\u65E6\u65FA\u6602\u670B\u676D\u68AF\u695A\u6B23\u6BC5\u6C70\u6C83\u6CE1\u6D8C\u6DD8\u6E20\u71D5\u72D0\u72D7\u73B2\u73CA\u7433\u7483\u74DC\u74F6\u7554\u764C\u7761\u77DB\u78A7\u7A46\u7A7F\u7A84\u7C97\u7D2F\u7FC1\u7FE0\u8000\u8017\u808C\u80AF\u8404\u8461\u8463\u8475\u8513\u85AA\u8679\u86CB\u871C\u87BA\u88F8\u8C8C\u8DF3\u8FC4\u901D\u9022\u906E\u9075\u9192\u91C7\u966A\u971E\u9910\u9B41\u9F0E\u9F20
TO_NORMALIZE_VI_CHARS=AEIOUYaeiouy\u00c2\u00ca\u00d4\u00e2\u00ea\u00f4\u0102\u0103\u01a0\u01a1\u01af\u01b0
DMARK_CLASS=\u0300\u0301\u0303\u0309\u0323
NORMALIZED_VI_CHARS_0300=\u00C0\u00C8\u00CC\u00D2\u00D9\u1EF2\u00E0\u00E8\u00EC\u00F2\u00F9\u1EF3\u1EA6\u1EC0\u1ED2\u1EA7\u1EC1\u1ED3\u1EB0\u1EB1\u1EDC\u1EDD\u1EEA\u1EEB
NORMALIZED_VI_CHARS_0301=\u00C1\u00C9\u00CD\u00D3\u00DA\u00DD\u00E1\u00E9\u00ED\u00F3\u00FA\u00FD\u1EA4\u1EBE\u1ED0\u1EA5\u1EBF\u1ED1\u1EAE\u1EAF\u1EDA\u1EDB\u1EE8\u1EE9
NORMALIZED_VI_CHARS_0303=\u00C3\u1EBC\u0128\u00D5\u0168\u1EF8\u00E3\u1EBD\u0129\u00F5\u0169\u1EF9\u1EAA\u1EC4\u1ED6\u1EAB\u1EC5\u1ED7\u1EB4\u1EB5\u1EE0\u1EE1\u1EEE\u1EEF
NORMALIZED_VI_CHARS_0309=\u1EA2\u1EBA\u1EC8\u1ECE\u1EE6\u1EF6\u1EA3\u1EBB\u1EC9\u1ECF\u1EE7\u1EF7\u1EA8\u1EC2\u1ED4\u1EA9\u1EC3\u1ED5\u1EB2\u1EB3\u1EDE\u1EDF\u1EEC\u1EED
NORMALIZED_VI_CHARS_0323=\u1EA0\u1EB8\u1ECA\u1ECC\u1EE4\u1EF4\u1EA1\u1EB9\u1ECB\u1ECD\u1EE5\u1EF5\u1EAC\u1EC6\u1ED8\u1EAD\u1EC7\u1ED9\u1EB6\u1EB7\u1EE2\u1EE3\u1EF0\u1EF1
text/langdetect/utils/messages.py 0 → 100644
View file @ b309ea1b
from os import path
class Messages(object):
MESSAGES_FILENAME = path.join(path.dirname(__file__), 'messages.properties')
def __init__(self):
self.messages = {}
with open(self.MESSAGES_FILENAME, 'r') as f:
for line in f:
key, _, value = line.strip().partition('=')
self.messages[key] = value.encode().decode('unicode_escape')
def get_string(self, key):
return self.messages.get(key, '!%s!' % key)
_messages = None
def get_string(key):
global _messages
if _messages is None:
_messages = Messages()
return _messages.get_string(key)
text/langdetect/utils/ngram.py 0 → 100644
View file @ b309ea1b
import re
import six
from . import messages
from .unicode_block import (
unicode_block,
UNICODE_BASIC_LATIN,
UNICODE_LATIN_1_SUPPLEMENT,
UNICODE_LATIN_EXTENDED_B,
UNICODE_GENERAL_PUNCTUATION,
UNICODE_ARABIC,
UNICODE_LATIN_EXTENDED_ADDITIONAL,
UNICODE_HIRAGANA,
UNICODE_KATAKANA,
UNICODE_BOPOMOFO,
UNICODE_BOPOMOFO_EXTENDED,
UNICODE_CJK_UNIFIED_IDEOGRAPHS,
UNICODE_HANGUL_SYLLABLES,
)
class NGram(object):
LATIN1_EXCLUDED = messages.get_string('NGram.LATIN1_EXCLUDE')
N_GRAM = 3
def __init__(self):
self.grams = ' '
self.capitalword = False
def add_char(self, ch):
'''Append a character into ngram buffer.'''
ch = self.normalize(ch)
last_char = self.grams[-1]
if last_char == ' ':
self.grams = ' '
self.capitalword = False
if ch == ' ':
return
elif len(self.grams) >= self.N_GRAM:
self.grams = self.grams[1:]
self.grams += ch
if ch.isupper():
if last_char.isupper():
self.capitalword = True
else:
self.capitalword = False
def get(self, n):
'''Get n-gram.'''
if self.capitalword:
return
if n < 1 or n > self.N_GRAM or len(self.grams) < n:
return
if n == 1:
ch = self.grams[-1]
if ch == ' ':
return
return ch
else:
return self.grams[-n:]
@classmethod
def normalize(cls, ch):
block = unicode_block(ch)
if block == UNICODE_BASIC_LATIN:
if ch < 'A' or ('Z' < ch < 'a') or 'z' < ch:
ch = ' '
elif block == UNICODE_LATIN_1_SUPPLEMENT:
if cls.LATIN1_EXCLUDED.find(ch) >= 0:
ch = ' '
elif block == UNICODE_LATIN_EXTENDED_B:
# normalization for Romanian
if ch == six.u('\u0219'): # Small S with comma below => with cedilla
ch = six.u('\u015f')
if ch == six.u('\u021b'): # Small T with comma below => with cedilla
ch = six.u('\u0163')
elif block == UNICODE_GENERAL_PUNCTUATION:
ch = ' '
elif block == UNICODE_ARABIC:
if ch == six.u('\u06cc'):
ch = six.u('\u064a') # Farsi yeh => Arabic yeh
elif block == UNICODE_LATIN_EXTENDED_ADDITIONAL:
if ch >= six.u('\u1ea0'):
ch = six.u('\u1ec3')
elif block == UNICODE_HIRAGANA:
ch = six.u('\u3042')
elif block == UNICODE_KATAKANA:
ch = six.u('\u30a2')
elif block in (UNICODE_BOPOMOFO, UNICODE_BOPOMOFO_EXTENDED):
ch = six.u('\u3105')
elif block == UNICODE_CJK_UNIFIED_IDEOGRAPHS:
ch = cls.CJK_MAP.get(ch, ch)
elif block == UNICODE_HANGUL_SYLLABLES:
ch = six.u('\uac00')
return ch
@classmethod
def normalize_vi(cls, text):
'''Normalizer for Vietnamese.
Normalize Alphabet + Diacritical Mark(U+03xx) into U+1Exx.
'''
def repl(m):
alphabet = cls.TO_NORMALIZE_VI_CHARS.find(m.group(1))
dmark = cls.DMARK_CLASS.find(m.group(2)) # Diacritical Mark
return cls.NORMALIZED_VI_CHARS[dmark][alphabet]
return cls.ALPHABET_WITH_DMARK.sub(repl, text)
NORMALIZED_VI_CHARS = [
messages.get_string('NORMALIZED_VI_CHARS_0300'),
messages.get_string('NORMALIZED_VI_CHARS_0301'),
messages.get_string('NORMALIZED_VI_CHARS_0303'),
messages.get_string('NORMALIZED_VI_CHARS_0309'),
messages.get_string('NORMALIZED_VI_CHARS_0323')]
TO_NORMALIZE_VI_CHARS = messages.get_string('TO_NORMALIZE_VI_CHARS')
DMARK_CLASS = messages.get_string('DMARK_CLASS')
ALPHABET_WITH_DMARK = re.compile(
'([' + TO_NORMALIZE_VI_CHARS + '])([' + DMARK_CLASS + '])',
re.UNICODE)
# CJK Kanji Normalization Mapping
CJK_CLASS = [
messages.get_string('NGram.KANJI_1_0'),
messages.get_string('NGram.KANJI_1_2'),
messages.get_string('NGram.KANJI_1_4'),
messages.get_string('NGram.KANJI_1_8'),
messages.get_string('NGram.KANJI_1_11'),
messages.get_string('NGram.KANJI_1_12'),
messages.get_string('NGram.KANJI_1_13'),
messages.get_string('NGram.KANJI_1_14'),
messages.get_string('NGram.KANJI_1_16'),
messages.get_string('NGram.KANJI_1_18'),
messages.get_string('NGram.KANJI_1_22'),
messages.get_string('NGram.KANJI_1_27'),
messages.get_string('NGram.KANJI_1_29'),
messages.get_string('NGram.KANJI_1_31'),
messages.get_string('NGram.KANJI_1_35'),
messages.get_string('NGram.KANJI_2_0'),
messages.get_string('NGram.KANJI_2_1'),
messages.get_string('NGram.KANJI_2_4'),
messages.get_string('NGram.KANJI_2_9'),
messages.get_string('NGram.KANJI_2_10'),
messages.get_string('NGram.KANJI_2_11'),
messages.get_string('NGram.KANJI_2_12'),
messages.get_string('NGram.KANJI_2_13'),
messages.get_string('NGram.KANJI_2_15'),
messages.get_string('NGram.KANJI_2_16'),
messages.get_string('NGram.KANJI_2_18'),
messages.get_string('NGram.KANJI_2_21'),
messages.get_string('NGram.KANJI_2_22'),
messages.get_string('NGram.KANJI_2_23'),
messages.get_string('NGram.KANJI_2_28'),
messages.get_string('NGram.KANJI_2_29'),
messages.get_string('NGram.KANJI_2_30'),
messages.get_string('NGram.KANJI_2_31'),
messages.get_string('NGram.KANJI_2_32'),
messages.get_string('NGram.KANJI_2_35'),
messages.get_string('NGram.KANJI_2_36'),
messages.get_string('NGram.KANJI_2_37'),
messages.get_string('NGram.KANJI_2_38'),
messages.get_string('NGram.KANJI_3_1'),
messages.get_string('NGram.KANJI_3_2'),
messages.get_string('NGram.KANJI_3_3'),
messages.get_string('NGram.KANJI_3_4'),
messages.get_string('NGram.KANJI_3_5'),
messages.get_string('NGram.KANJI_3_8'),
messages.get_string('NGram.KANJI_3_9'),
messages.get_string('NGram.KANJI_3_11'),
messages.get_string('NGram.KANJI_3_12'),
messages.get_string('NGram.KANJI_3_13'),
messages.get_string('NGram.KANJI_3_15'),
messages.get_string('NGram.KANJI_3_16'),
messages.get_string('NGram.KANJI_3_18'),
messages.get_string('NGram.KANJI_3_19'),
messages.get_string('NGram.KANJI_3_22'),
messages.get_string('NGram.KANJI_3_23'),
messages.get_string('NGram.KANJI_3_27'),
messages.get_string('NGram.KANJI_3_29'),
messages.get_string('NGram.KANJI_3_30'),
messages.get_string('NGram.KANJI_3_31'),
messages.get_string('NGram.KANJI_3_32'),
messages.get_string('NGram.KANJI_3_35'),
messages.get_string('NGram.KANJI_3_36'),
messages.get_string('NGram.KANJI_3_37'),
messages.get_string('NGram.KANJI_3_38'),
messages.get_string('NGram.KANJI_4_0'),
messages.get_string('NGram.KANJI_4_9'),
messages.get_string('NGram.KANJI_4_10'),
messages.get_string('NGram.KANJI_4_16'),
messages.get_string('NGram.KANJI_4_17'),
messages.get_string('NGram.KANJI_4_18'),
messages.get_string('NGram.KANJI_4_22'),
messages.get_string('NGram.KANJI_4_24'),
messages.get_string('NGram.KANJI_4_28'),
messages.get_string('NGram.KANJI_4_34'),
messages.get_string('NGram.KANJI_4_39'),
messages.get_string('NGram.KANJI_5_10'),
messages.get_string('NGram.KANJI_5_11'),
messages.get_string('NGram.KANJI_5_12'),
messages.get_string('NGram.KANJI_5_13'),
messages.get_string('NGram.KANJI_5_14'),
messages.get_string('NGram.KANJI_5_18'),
messages.get_string('NGram.KANJI_5_26'),
messages.get_string('NGram.KANJI_5_29'),
messages.get_string('NGram.KANJI_5_34'),
messages.get_string('NGram.KANJI_5_39'),
messages.get_string('NGram.KANJI_6_0'),
messages.get_string('NGram.KANJI_6_3'),
messages.get_string('NGram.KANJI_6_9'),
messages.get_string('NGram.KANJI_6_10'),
messages.get_string('NGram.KANJI_6_11'),
messages.get_string('NGram.KANJI_6_12'),
messages.get_string('NGram.KANJI_6_16'),
messages.get_string('NGram.KANJI_6_18'),
messages.get_string('NGram.KANJI_6_20'),
messages.get_string('NGram.KANJI_6_21'),
messages.get_string('NGram.KANJI_6_22'),
messages.get_string('NGram.KANJI_6_23'),
messages.get_string('NGram.KANJI_6_25'),
messages.get_string('NGram.KANJI_6_28'),
messages.get_string('NGram.KANJI_6_29'),
messages.get_string('NGram.KANJI_6_30'),
messages.get_string('NGram.KANJI_6_32'),
messages.get_string('NGram.KANJI_6_34'),
messages.get_string('NGram.KANJI_6_35'),
messages.get_string('NGram.KANJI_6_37'),
messages.get_string('NGram.KANJI_6_39'),
messages.get_string('NGram.KANJI_7_0'),
messages.get_string('NGram.KANJI_7_3'),
messages.get_string('NGram.KANJI_7_6'),
messages.get_string('NGram.KANJI_7_7'),
messages.get_string('NGram.KANJI_7_9'),
messages.get_string('NGram.KANJI_7_11'),
messages.get_string('NGram.KANJI_7_12'),
messages.get_string('NGram.KANJI_7_13'),
messages.get_string('NGram.KANJI_7_16'),
messages.get_string('NGram.KANJI_7_18'),
messages.get_string('NGram.KANJI_7_19'),
messages.get_string('NGram.KANJI_7_20'),
messages.get_string('NGram.KANJI_7_21'),
messages.get_string('NGram.KANJI_7_23'),
messages.get_string('NGram.KANJI_7_25'),
messages.get_string('NGram.KANJI_7_28'),
messages.get_string('NGram.KANJI_7_29'),
messages.get_string('NGram.KANJI_7_32'),
messages.get_string('NGram.KANJI_7_33'),
messages.get_string('NGram.KANJI_7_35'),
messages.get_string('NGram.KANJI_7_37')]
CJK_MAP = {}
@classmethod
def _init_cjk_map(cls):
for cjk_list in cls.CJK_CLASS:
representative = cjk_list[0]
for ch in cjk_list:
cls.CJK_MAP[ch] = representative
NGram._init_cjk_map()
text/langdetect/utils/unicode_block.py 0 → 100644
View file @ b309ea1b
UNICODE_BASIC_LATIN = 1
UNICODE_LATIN_1_SUPPLEMENT = 2
UNICODE_LATIN_EXTENDED_A = 3
UNICODE_LATIN_EXTENDED_B = 4
UNICODE_IPA_EXTENSIONS = 5
UNICODE_SPACING_MODIFIER_LETTERS = 6
UNICODE_COMBINING_DIACRITICAL_MARKS = 7
UNICODE_GREEK_AND_COPTIC = 8
UNICODE_CYRILLIC = 9
UNICODE_CYRILLIC_SUPPLEMENT = 10
UNICODE_ARMENIAN = 11
UNICODE_HEBREW = 12
UNICODE_ARABIC = 13
UNICODE_SYRIAC = 14
UNICODE_ARABIC_SUPPLEMENT = 15
UNICODE_THAANA = 16
UNICODE_NKO = 17
UNICODE_SAMARITAN = 18
UNICODE_MANDAIC = 19
UNICODE_ARABIC_EXTENDED_A = 20
UNICODE_DEVANAGARI = 21
UNICODE_BENGALI = 22
UNICODE_GURMUKHI = 23
UNICODE_GUJARATI = 24
UNICODE_ORIYA = 25
UNICODE_TAMIL = 26
UNICODE_TELUGU = 27
UNICODE_KANNADA = 28
UNICODE_MALAYALAM = 29
UNICODE_SINHALA = 30
UNICODE_THAI = 31
UNICODE_LAO = 32
UNICODE_TIBETAN = 33
UNICODE_MYANMAR = 34
UNICODE_GEORGIAN = 35
UNICODE_HANGUL_JAMO = 36
UNICODE_ETHIOPIC = 37
UNICODE_ETHIOPIC_SUPPLEMENT = 38
UNICODE_CHEROKEE = 39
UNICODE_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = 40
UNICODE_OGHAM = 41
UNICODE_RUNIC = 42
UNICODE_TAGALOG = 43
UNICODE_HANUNOO = 44
UNICODE_BUHID = 45
UNICODE_TAGBANWA = 46
UNICODE_KHMER = 47
UNICODE_MONGOLIAN = 48
UNICODE_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 49
UNICODE_LIMBU = 50
UNICODE_TAI_LE = 51
UNICODE_NEW_TAI_LUE = 52
UNICODE_KHMER_SYMBOLS = 53
UNICODE_BUGINESE = 54
UNICODE_TAI_THAM = 55
UNICODE_BALINESE = 56
UNICODE_SUNDANESE = 57
UNICODE_BATAK = 58
UNICODE_LEPCHA = 59
UNICODE_OL_CHIKI = 60
UNICODE_SUNDANESE_SUPPLEMENT = 61
UNICODE_VEDIC_EXTENSIONS = 62
UNICODE_PHONETIC_EXTENSIONS = 63
UNICODE_PHONETIC_EXTENSIONS_SUPPLEMENT = 64
UNICODE_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 65
UNICODE_LATIN_EXTENDED_ADDITIONAL = 66
UNICODE_GREEK_EXTENDED = 67
UNICODE_GENERAL_PUNCTUATION = 68
UNICODE_SUPERSCRIPTS_AND_SUBSCRIPTS = 69
UNICODE_CURRENCY_SYMBOLS = 70
UNICODE_COMBINING_DIACRITICAL_MARKS_FOR_SYMBOLS = 71
UNICODE_LETTERLIKE_SYMBOLS = 72
UNICODE_NUMBER_FORMS = 73
UNICODE_ARROWS = 74
UNICODE_MATHEMATICAL_OPERATORS = 75
UNICODE_MISCELLANEOUS_TECHNICAL = 76
UNICODE_CONTROL_PICTURES = 77
UNICODE_OPTICAL_CHARACTER_RECOGNITION = 78
UNICODE_ENCLOSED_ALPHANUMERICS = 79
UNICODE_BOX_DRAWING = 80
UNICODE_BLOCK_ELEMENTS = 81
UNICODE_GEOMETRIC_SHAPES = 82
UNICODE_MISCELLANEOUS_SYMBOLS = 83
UNICODE_DINGBATS = 84
UNICODE_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 85
UNICODE_SUPPLEMENTAL_ARROWS_A = 86
UNICODE_BRAILLE_PATTERNS = 87
UNICODE_SUPPLEMENTAL_ARROWS_B = 88
UNICODE_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 89
UNICODE_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 90
UNICODE_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 91
UNICODE_GLAGOLITIC = 92
UNICODE_LATIN_EXTENDED_C = 93
UNICODE_COPTIC = 94
UNICODE_GEORGIAN_SUPPLEMENT = 95
UNICODE_TIFINAGH = 96
UNICODE_ETHIOPIC_EXTENDED = 97
UNICODE_CYRILLIC_EXTENDED_A = 98
UNICODE_SUPPLEMENTAL_PUNCTUATION = 99
UNICODE_CJK_RADICALS_SUPPLEMENT = 100
UNICODE_KANGXI_RADICALS = 101
UNICODE_IDEOGRAPHIC_DESCRIPTION_CHARACTERS = 102
UNICODE_CJK_SYMBOLS_AND_PUNCTUATION = 103
UNICODE_HIRAGANA = 104
UNICODE_KATAKANA = 105
UNICODE_BOPOMOFO = 106
UNICODE_HANGUL_COMPATIBILITY_JAMO = 107
UNICODE_KANBUN = 108
UNICODE_BOPOMOFO_EXTENDED = 109
UNICODE_CJK_STROKES = 110
UNICODE_KATAKANA_PHONETIC_EXTENSIONS = 111
UNICODE_ENCLOSED_CJK_LETTERS_AND_MONTHS = 112
UNICODE_CJK_COMPATIBILITY = 113
UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = 114
UNICODE_YIJING_HEXAGRAM_SYMBOLS = 115
UNICODE_CJK_UNIFIED_IDEOGRAPHS = 116
UNICODE_YI_SYLLABLES = 117
UNICODE_YI_RADICALS = 118
UNICODE_LISU = 119
UNICODE_VAI = 120
UNICODE_CYRILLIC_EXTENDED_B = 121
UNICODE_BAMUM = 122
UNICODE_MODIFIER_TONE_LETTERS = 123
UNICODE_LATIN_EXTENDED_D = 124
UNICODE_SYLOTI_NAGRI = 125
UNICODE_COMMON_INDIC_NUMBER_FORMS = 126
UNICODE_PHAGS_PA = 127
UNICODE_SAURASHTRA = 128
UNICODE_DEVANAGARI_EXTENDED = 129
UNICODE_KAYAH_LI = 130
UNICODE_REJANG = 131
UNICODE_HANGUL_JAMO_EXTENDED_A = 132
UNICODE_JAVANESE = 133
UNICODE_CHAM = 134
UNICODE_MYANMAR_EXTENDED_A = 135
UNICODE_TAI_VIET = 136
UNICODE_MEETEI_MAYEK_EXTENSIONS = 137
UNICODE_ETHIOPIC_EXTENDED_A = 138
UNICODE_MEETEI_MAYEK = 139
UNICODE_HANGUL_SYLLABLES = 140
UNICODE_HANGUL_JAMO_EXTENDED_B = 141
UNICODE_HIGH_SURROGATES = 142
UNICODE_HIGH_PRIVATE_USE_SURROGATES = 143
UNICODE_LOW_SURROGATES = 144
UNICODE_PRIVATE_USE_AREA = 145
UNICODE_CJK_COMPATIBILITY_IDEOGRAPHS = 146
UNICODE_ALPHABETIC_PRESENTATION_FORMS = 147
UNICODE_ARABIC_PRESENTATION_FORMS_A = 148
UNICODE_VARIATION_SELECTORS = 149
UNICODE_VERTICAL_FORMS = 150
UNICODE_COMBINING_HALF_MARKS = 151
UNICODE_CJK_COMPATIBILITY_FORMS = 152
UNICODE_SMALL_FORM_VARIANTS = 153
UNICODE_ARABIC_PRESENTATION_FORMS_B = 154
UNICODE_HALFWIDTH_AND_FULLWIDTH_FORMS = 155
UNICODE_SPECIALS = 156
UNICODE_LINEAR_B_SYLLABARY = 157
UNICODE_LINEAR_B_IDEOGRAMS = 158
UNICODE_AEGEAN_NUMBERS = 159
UNICODE_ANCIENT_GREEK_NUMBERS = 160
UNICODE_ANCIENT_SYMBOLS = 161
UNICODE_PHAISTOS_DISC = 162
UNICODE_LYCIAN = 163
UNICODE_CARIAN = 164
UNICODE_OLD_ITALIC = 165
UNICODE_GOTHIC = 166
UNICODE_UGARITIC = 167
UNICODE_OLD_PERSIAN = 168
UNICODE_DESERET = 169
UNICODE_SHAVIAN = 170
UNICODE_OSMANYA = 171
UNICODE_CYPRIOT_SYLLABARY = 172
UNICODE_IMPERIAL_ARAMAIC = 173
UNICODE_PHOENICIAN = 174
UNICODE_LYDIAN = 175
UNICODE_MEROITIC_HIEROGLYPHS = 176
UNICODE_MEROITIC_CURSIVE = 177
UNICODE_KHAROSHTHI = 178
UNICODE_OLD_SOUTH_ARABIAN = 179
UNICODE_AVESTAN = 180
UNICODE_INSCRIPTIONAL_PARTHIAN = 181
UNICODE_INSCRIPTIONAL_PAHLAVI = 182
UNICODE_OLD_TURKIC = 183
UNICODE_RUMI_NUMERAL_SYMBOLS = 184
UNICODE_BRAHMI = 185
UNICODE_KAITHI = 186
UNICODE_SORA_SOMPENG = 187
UNICODE_CHAKMA = 188
UNICODE_SHARADA = 189
UNICODE_TAKRI = 190
UNICODE_CUNEIFORM = 191
UNICODE_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 192
UNICODE_EGYPTIAN_HIEROGLYPHS = 193
UNICODE_BAMUM_SUPPLEMENT = 194
UNICODE_MIAO = 195
UNICODE_KANA_SUPPLEMENT = 196
UNICODE_BYZANTINE_MUSICAL_SYMBOLS = 197
UNICODE_MUSICAL_SYMBOLS = 198
UNICODE_ANCIENT_GREEK_MUSICAL_NOTATION = 199
UNICODE_TAI_XUAN_JING_SYMBOLS = 200
UNICODE_COUNTING_ROD_NUMERALS = 201
UNICODE_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 202
UNICODE_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 203
UNICODE_MAHJONG_TILES = 204
UNICODE_DOMINO_TILES = 205
UNICODE_PLAYING_CARDS = 206
UNICODE_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 207
UNICODE_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 208
UNICODE_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 209
UNICODE_EMOTICONS = 210
UNICODE_TRANSPORT_AND_MAP_SYMBOLS = 211
UNICODE_ALCHEMICAL_SYMBOLS = 212
UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 213
UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 214
UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 215
UNICODE_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 216
UNICODE_TAGS = 217
UNICODE_VARIATION_SELECTORS_SUPPLEMENT = 218
UNICODE_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 219
UNICODE_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 220
_unicode_blocks = [
(UNICODE_BASIC_LATIN, 0x0000, 0x007F),
(UNICODE_LATIN_1_SUPPLEMENT, 0x0080, 0x00FF),
(UNICODE_LATIN_EXTENDED_A, 0x0100, 0x017F),
(UNICODE_LATIN_EXTENDED_B, 0x0180, 0x024F),
(UNICODE_IPA_EXTENSIONS, 0x0250, 0x02AF),
(UNICODE_SPACING_MODIFIER_LETTERS, 0x02B0, 0x02FF),
(UNICODE_COMBINING_DIACRITICAL_MARKS, 0x0300, 0x036F),
(UNICODE_GREEK_AND_COPTIC, 0x0370, 0x03FF),
(UNICODE_CYRILLIC, 0x0400, 0x04FF),
(UNICODE_CYRILLIC_SUPPLEMENT, 0x0500, 0x052F),
(UNICODE_ARMENIAN, 0x0530, 0x058F),
(UNICODE_HEBREW, 0x0590, 0x05FF),
(UNICODE_ARABIC, 0x0600, 0x06FF),
(UNICODE_SYRIAC, 0x0700, 0x074F),
(UNICODE_ARABIC_SUPPLEMENT, 0x0750, 0x077F),
(UNICODE_THAANA, 0x0780, 0x07BF),
(UNICODE_NKO, 0x07C0, 0x07FF),
(UNICODE_SAMARITAN, 0x0800, 0x083F),
(UNICODE_MANDAIC, 0x0840, 0x085F),
(UNICODE_ARABIC_EXTENDED_A, 0x08A0, 0x08FF),
(UNICODE_DEVANAGARI, 0x0900, 0x097F),
(UNICODE_BENGALI, 0x0980, 0x09FF),
(UNICODE_GURMUKHI, 0x0A00, 0x0A7F),
(UNICODE_GUJARATI, 0x0A80, 0x0AFF),
(UNICODE_ORIYA, 0x0B00, 0x0B7F),
(UNICODE_TAMIL, 0x0B80, 0x0BFF),
(UNICODE_TELUGU, 0x0C00, 0x0C7F),
(UNICODE_KANNADA, 0x0C80, 0x0CFF),
(UNICODE_MALAYALAM, 0x0D00, 0x0D7F),
(UNICODE_SINHALA, 0x0D80, 0x0DFF),
(UNICODE_THAI, 0x0E00, 0x0E7F),
(UNICODE_LAO, 0x0E80, 0x0EFF),
(UNICODE_TIBETAN, 0x0F00, 0x0FFF),
(UNICODE_MYANMAR, 0x1000, 0x109F),
(UNICODE_GEORGIAN, 0x10A0, 0x10FF),
(UNICODE_HANGUL_JAMO, 0x1100, 0x11FF),
(UNICODE_ETHIOPIC, 0x1200, 0x137F),
(UNICODE_ETHIOPIC_SUPPLEMENT, 0x1380, 0x139F),
(UNICODE_CHEROKEE, 0x13A0, 0x13FF),
(UNICODE_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS, 0x1400, 0x167F),
(UNICODE_OGHAM, 0x1680, 0x169F),
(UNICODE_RUNIC, 0x16A0, 0x16FF),
(UNICODE_TAGALOG, 0x1700, 0x171F),
(UNICODE_HANUNOO, 0x1720, 0x173F),
(UNICODE_BUHID, 0x1740, 0x175F),
(UNICODE_TAGBANWA, 0x1760, 0x177F),
(UNICODE_KHMER, 0x1780, 0x17FF),
(UNICODE_MONGOLIAN, 0x1800, 0x18AF),
(UNICODE_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED, 0x18B0, 0x18FF),
(UNICODE_LIMBU, 0x1900, 0x194F),
(UNICODE_TAI_LE, 0x1950, 0x197F),
(UNICODE_NEW_TAI_LUE, 0x1980, 0x19DF),
(UNICODE_KHMER_SYMBOLS, 0x19E0, 0x19FF),
(UNICODE_BUGINESE, 0x1A00, 0x1A1F),
(UNICODE_TAI_THAM, 0x1A20, 0x1AAF),
(UNICODE_BALINESE, 0x1B00, 0x1B7F),
(UNICODE_SUNDANESE, 0x1B80, 0x1BBF),
(UNICODE_BATAK, 0x1BC0, 0x1BFF),
(UNICODE_LEPCHA, 0x1C00, 0x1C4F),
(UNICODE_OL_CHIKI, 0x1C50, 0x1C7F),
(UNICODE_SUNDANESE_SUPPLEMENT, 0x1CC0, 0x1CCF),
(UNICODE_VEDIC_EXTENSIONS, 0x1CD0, 0x1CFF),
(UNICODE_PHONETIC_EXTENSIONS, 0x1D00, 0x1D7F),
(UNICODE_PHONETIC_EXTENSIONS_SUPPLEMENT, 0x1D80, 0x1DBF),
(UNICODE_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT, 0x1DC0, 0x1DFF),
(UNICODE_LATIN_EXTENDED_ADDITIONAL, 0x1E00, 0x1EFF),
(UNICODE_GREEK_EXTENDED, 0x1F00, 0x1FFF),
(UNICODE_GENERAL_PUNCTUATION, 0x2000, 0x206F),
(UNICODE_SUPERSCRIPTS_AND_SUBSCRIPTS, 0x2070, 0x209F),
(UNICODE_CURRENCY_SYMBOLS, 0x20A0, 0x20CF),
(UNICODE_COMBINING_DIACRITICAL_MARKS_FOR_SYMBOLS, 0x20D0, 0x20FF),
(UNICODE_LETTERLIKE_SYMBOLS, 0x2100, 0x214F),
(UNICODE_NUMBER_FORMS, 0x2150, 0x218F),
(UNICODE_ARROWS, 0x2190, 0x21FF),
(UNICODE_MATHEMATICAL_OPERATORS, 0x2200, 0x22FF),
(UNICODE_MISCELLANEOUS_TECHNICAL, 0x2300, 0x23FF),
(UNICODE_CONTROL_PICTURES, 0x2400, 0x243F),
(UNICODE_OPTICAL_CHARACTER_RECOGNITION, 0x2440, 0x245F),
(UNICODE_ENCLOSED_ALPHANUMERICS, 0x2460, 0x24FF),
(UNICODE_BOX_DRAWING, 0x2500, 0x257F),
(UNICODE_BLOCK_ELEMENTS, 0x2580, 0x259F),
(UNICODE_GEOMETRIC_SHAPES, 0x25A0, 0x25FF),
(UNICODE_MISCELLANEOUS_SYMBOLS, 0x2600, 0x26FF),
(UNICODE_DINGBATS, 0x2700, 0x27BF),
(UNICODE_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A, 0x27C0, 0x27EF),
(UNICODE_SUPPLEMENTAL_ARROWS_A, 0x27F0, 0x27FF),
(UNICODE_BRAILLE_PATTERNS, 0x2800, 0x28FF),
(UNICODE_SUPPLEMENTAL_ARROWS_B, 0x2900, 0x297F),
(UNICODE_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B, 0x2980, 0x29FF),
(UNICODE_SUPPLEMENTAL_MATHEMATICAL_OPERATORS, 0x2A00, 0x2AFF),
(UNICODE_MISCELLANEOUS_SYMBOLS_AND_ARROWS, 0x2B00, 0x2BFF),
(UNICODE_GLAGOLITIC, 0x2C00, 0x2C5F),
(UNICODE_LATIN_EXTENDED_C, 0x2C60, 0x2C7F),
(UNICODE_COPTIC, 0x2C80, 0x2CFF),
(UNICODE_GEORGIAN_SUPPLEMENT, 0x2D00, 0x2D2F),
(UNICODE_TIFINAGH, 0x2D30, 0x2D7F),
(UNICODE_ETHIOPIC_EXTENDED, 0x2D80, 0x2DDF),
(UNICODE_CYRILLIC_EXTENDED_A, 0x2DE0, 0x2DFF),
(UNICODE_SUPPLEMENTAL_PUNCTUATION, 0x2E00, 0x2E7F),
(UNICODE_CJK_RADICALS_SUPPLEMENT, 0x2E80, 0x2EFF),
(UNICODE_KANGXI_RADICALS, 0x2F00, 0x2FDF),
(UNICODE_IDEOGRAPHIC_DESCRIPTION_CHARACTERS, 0x2FF0, 0x2FFF),
(UNICODE_CJK_SYMBOLS_AND_PUNCTUATION, 0x3000, 0x303F),
(UNICODE_HIRAGANA, 0x3040, 0x309F),
(UNICODE_KATAKANA, 0x30A0, 0x30FF),
(UNICODE_BOPOMOFO, 0x3100, 0x312F),
(UNICODE_HANGUL_COMPATIBILITY_JAMO, 0x3130, 0x318F),
(UNICODE_KANBUN, 0x3190, 0x319F),
(UNICODE_BOPOMOFO_EXTENDED, 0x31A0, 0x31BF),
(UNICODE_CJK_STROKES, 0x31C0, 0x31EF),
(UNICODE_KATAKANA_PHONETIC_EXTENSIONS, 0x31F0, 0x31FF),
(UNICODE_ENCLOSED_CJK_LETTERS_AND_MONTHS, 0x3200, 0x32FF),
(UNICODE_CJK_COMPATIBILITY, 0x3300, 0x33FF),
(UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A, 0x3400, 0x4DBF),
(UNICODE_YIJING_HEXAGRAM_SYMBOLS, 0x4DC0, 0x4DFF),
(UNICODE_CJK_UNIFIED_IDEOGRAPHS, 0x4E00, 0x9FFF),
(UNICODE_YI_SYLLABLES, 0xA000, 0xA48F),
(UNICODE_YI_RADICALS, 0xA490, 0xA4CF),
(UNICODE_LISU, 0xA4D0, 0xA4FF),
(UNICODE_VAI, 0xA500, 0xA63F),
(UNICODE_CYRILLIC_EXTENDED_B, 0xA640, 0xA69F),
(UNICODE_BAMUM, 0xA6A0, 0xA6FF),
(UNICODE_MODIFIER_TONE_LETTERS, 0xA700, 0xA71F),
(UNICODE_LATIN_EXTENDED_D, 0xA720, 0xA7FF),
(UNICODE_SYLOTI_NAGRI, 0xA800, 0xA82F),
(UNICODE_COMMON_INDIC_NUMBER_FORMS, 0xA830, 0xA83F),
(UNICODE_PHAGS_PA, 0xA840, 0xA87F),
(UNICODE_SAURASHTRA, 0xA880, 0xA8DF),
(UNICODE_DEVANAGARI_EXTENDED, 0xA8E0, 0xA8FF),
(UNICODE_KAYAH_LI, 0xA900, 0xA92F),
(UNICODE_REJANG, 0xA930, 0xA95F),
(UNICODE_HANGUL_JAMO_EXTENDED_A, 0xA960, 0xA97F),
(UNICODE_JAVANESE, 0xA980, 0xA9DF),
(UNICODE_CHAM, 0xAA00, 0xAA5F),
(UNICODE_MYANMAR_EXTENDED_A, 0xAA60, 0xAA7F),
(UNICODE_TAI_VIET, 0xAA80, 0xAADF),
(UNICODE_MEETEI_MAYEK_EXTENSIONS, 0xAAE0, 0xAAFF),
(UNICODE_ETHIOPIC_EXTENDED_A, 0xAB00, 0xAB2F),
(UNICODE_MEETEI_MAYEK, 0xABC0, 0xABFF),
(UNICODE_HANGUL_SYLLABLES, 0xAC00, 0xD7AF),
(UNICODE_HANGUL_JAMO_EXTENDED_B, 0xD7B0, 0xD7FF),
(UNICODE_HIGH_SURROGATES, 0xD800, 0xDB7F),
(UNICODE_HIGH_PRIVATE_USE_SURROGATES, 0xDB80, 0xDBFF),
(UNICODE_LOW_SURROGATES, 0xDC00, 0xDFFF),
(UNICODE_PRIVATE_USE_AREA, 0xE000, 0xF8FF),
(UNICODE_CJK_COMPATIBILITY_IDEOGRAPHS, 0xF900, 0xFAFF),
(UNICODE_ALPHABETIC_PRESENTATION_FORMS, 0xFB00, 0xFB4F),
(UNICODE_ARABIC_PRESENTATION_FORMS_A, 0xFB50, 0xFDFF),
(UNICODE_VARIATION_SELECTORS, 0xFE00, 0xFE0F),
(UNICODE_VERTICAL_FORMS, 0xFE10, 0xFE1F),
(UNICODE_COMBINING_HALF_MARKS, 0xFE20, 0xFE2F),
(UNICODE_CJK_COMPATIBILITY_FORMS, 0xFE30, 0xFE4F),
(UNICODE_SMALL_FORM_VARIANTS, 0xFE50, 0xFE6F),
(UNICODE_ARABIC_PRESENTATION_FORMS_B, 0xFE70, 0xFEFF),
(UNICODE_HALFWIDTH_AND_FULLWIDTH_FORMS, 0xFF00, 0xFFEF),
(UNICODE_SPECIALS, 0xFFF0, 0xFFFF),
(UNICODE_LINEAR_B_SYLLABARY, 0x10000, 0x1007F),
(UNICODE_LINEAR_B_IDEOGRAMS, 0x10080, 0x100FF),
(UNICODE_AEGEAN_NUMBERS, 0x10100, 0x1013F),
(UNICODE_ANCIENT_GREEK_NUMBERS, 0x10140, 0x1018F),
(UNICODE_ANCIENT_SYMBOLS, 0x10190, 0x101CF),
(UNICODE_PHAISTOS_DISC, 0x101D0, 0x101FF),
(UNICODE_LYCIAN, 0x10280, 0x1029F),
(UNICODE_CARIAN, 0x102A0, 0x102DF),
(UNICODE_OLD_ITALIC, 0x10300, 0x1032F),
(UNICODE_GOTHIC, 0x10330, 0x1034F),
(UNICODE_UGARITIC, 0x10380, 0x1039F),
(UNICODE_OLD_PERSIAN, 0x103A0, 0x103DF),
(UNICODE_DESERET, 0x10400, 0x1044F),
(UNICODE_SHAVIAN, 0x10450, 0x1047F),
(UNICODE_OSMANYA, 0x10480, 0x104AF),
(UNICODE_CYPRIOT_SYLLABARY, 0x10800, 0x1083F),
(UNICODE_IMPERIAL_ARAMAIC, 0x10840, 0x1085F),
(UNICODE_PHOENICIAN, 0x10900, 0x1091F),
(UNICODE_LYDIAN, 0x10920, 0x1093F),
(UNICODE_MEROITIC_HIEROGLYPHS, 0x10980, 0x1099F),
(UNICODE_MEROITIC_CURSIVE, 0x109A0, 0x109FF),
(UNICODE_KHAROSHTHI, 0x10A00, 0x10A5F),
(UNICODE_OLD_SOUTH_ARABIAN, 0x10A60, 0x10A7F),
(UNICODE_AVESTAN, 0x10B00, 0x10B3F),
(UNICODE_INSCRIPTIONAL_PARTHIAN, 0x10B40, 0x10B5F),
(UNICODE_INSCRIPTIONAL_PAHLAVI, 0x10B60, 0x10B7F),
(UNICODE_OLD_TURKIC, 0x10C00, 0x10C4F),
(UNICODE_RUMI_NUMERAL_SYMBOLS, 0x10E60, 0x10E7F),
(UNICODE_BRAHMI, 0x11000, 0x1107F),
(UNICODE_KAITHI, 0x11080, 0x110CF),
(UNICODE_SORA_SOMPENG, 0x110D0, 0x110FF),
(UNICODE_CHAKMA, 0x11100, 0x1114F),
(UNICODE_SHARADA, 0x11180, 0x111DF),
(UNICODE_TAKRI, 0x11680, 0x116CF),
(UNICODE_CUNEIFORM, 0x12000, 0x123FF),
(UNICODE_CUNEIFORM_NUMBERS_AND_PUNCTUATION, 0x12400, 0x1247F),
(UNICODE_EGYPTIAN_HIEROGLYPHS, 0x13000, 0x1342F),
(UNICODE_BAMUM_SUPPLEMENT, 0x16800, 0x16A3F),
(UNICODE_MIAO, 0x16F00, 0x16F9F),
(UNICODE_KANA_SUPPLEMENT, 0x1B000, 0x1B0FF),
(UNICODE_BYZANTINE_MUSICAL_SYMBOLS, 0x1D000, 0x1D0FF),
(UNICODE_MUSICAL_SYMBOLS, 0x1D100, 0x1D1FF),
(UNICODE_ANCIENT_GREEK_MUSICAL_NOTATION, 0x1D200, 0x1D24F),
(UNICODE_TAI_XUAN_JING_SYMBOLS, 0x1D300, 0x1D35F),
(UNICODE_COUNTING_ROD_NUMERALS, 0x1D360, 0x1D37F),
(UNICODE_MATHEMATICAL_ALPHANUMERIC_SYMBOLS, 0x1D400, 0x1D7FF),
(UNICODE_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS, 0x1EE00, 0x1EEFF),
(UNICODE_MAHJONG_TILES, 0x1F000, 0x1F02F),
(UNICODE_DOMINO_TILES, 0x1F030, 0x1F09F),
(UNICODE_PLAYING_CARDS, 0x1F0A0, 0x1F0FF),
(UNICODE_ENCLOSED_ALPHANUMERIC_SUPPLEMENT, 0x1F100, 0x1F1FF),
(UNICODE_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT, 0x1F200, 0x1F2FF),
(UNICODE_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS, 0x1F300, 0x1F5FF),
(UNICODE_EMOTICONS, 0x1F600, 0x1F64F),
(UNICODE_TRANSPORT_AND_MAP_SYMBOLS, 0x1F680, 0x1F6FF),
(UNICODE_ALCHEMICAL_SYMBOLS, 0x1F700, 0x1F77F),
(UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B, 0x20000, 0x2A6DF),
(UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C, 0x2A700, 0x2B73F),
(UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D, 0x2B740, 0x2B81F),
(UNICODE_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT, 0x2F800, 0x2FA1F),
(UNICODE_TAGS, 0xE0000, 0xE007F),
(UNICODE_VARIATION_SELECTORS_SUPPLEMENT, 0xE0100, 0xE01EF),
(UNICODE_SUPPLEMENTARY_PRIVATE_USE_AREA_A, 0xF0000, 0xFFFFF),
(UNICODE_SUPPLEMENTARY_PRIVATE_USE_AREA_B, 0x100000, 0x10FFFF),
]
NUM_BLOCKS = len(_unicode_blocks)
def unicode_block(ch):
'''Return the Unicode block name for ch, or None if ch has no block.'''
cp = ord(ch)
# special case basic latin
if cp <= 0x7F:
return UNICODE_BASIC_LATIN
# binary search for the correct block
be, en = 0, NUM_BLOCKS - 1
while be <= en:
mid = (be+en) >> 1
name, start, end = _unicode_blocks[mid]
if start <= cp <= end:
return name
if cp < start:
en = mid-1
else:
be = mid+1
text/mandarin.py 0 → 100644
View file @ b309ea1b
import re
from pypinyin import lazy_pinyin, Style
from .custom_pypinyin_dict import phrase_pinyin_data
phrase_pinyin_data.load()
import jieba
from .cn2an import an2cn
# 标点符号正则
punc_map = {
"：": ",",
"；": ",",
"，": ",",
"。": ".",
"！": "!",
"？": "?",
"\n": ".",
"·": ",",
"、": ",",
"$": ".",
"“": "'",
"”": "'",
'"': "'",
"‘": "'",
"’": "'",
"（": "'",
"）": "'",
"(": "'",
")": "'",
"《": "'",
"》": "'",
"【": "'",
"】": "'",
"[": "'",
"]": "'",
"—": "-",
"～": "~",
"「": "'",
"」": "'",
"『": "'",
"』": "'",
}
punc_table = str.maketrans(punc_map)
# 数字正则化
number_pattern = re.compile(r'\d+(?:\.?\d+)?')
def replace_number(match):
return an2cn(match.group())
def normalize_number(text):
return number_pattern.sub(replace_number, text)
# get symbols of phones
def load_pinyin_symbols(path):
pinyin_dict={}
temp = []
with open(path, "r", encoding='utf-8') as f:
content = f.readlines()
for line in content:
cuts = line.strip().split(',')
pinyin = cuts[0]
phones = cuts[1].split(' ')
pinyin_dict[pinyin] = phones
temp.extend(phones)
temp = list(set(temp))
tone = []
for phone in temp:
for i in range(1, 6):
phone2 = phone + str(i)
tone.append(phone2)
print(sorted(tone, key=lambda x: len(x)))
return pinyin_dict
def load_pinyin_dict(path):
pinyin_dict = {}
with open(path, "r", encoding='utf-8') as f:
for line in f:
key, value = line.strip().split(',', 1)
pinyin_dict[key] = value.split()
return pinyin_dict
pinyin_dict = load_pinyin_dict('text/cnm3/ds_CNM3.txt')
def chinese_to_cnm3(text: str):
text = text.translate(punc_table)
text = normalize_number(text)
words = jieba.lcut(text, cut_all=False)
phones = []
for word in words:
pinyin_list = lazy_pinyin(word, style=Style.TONE3, neutral_tone_with_five=True)
for pinyin in pinyin_list:
if pinyin[-1].isdigit():
tone = pinyin[-1]
syllable = pinyin[:-1]
phone = pinyin_dict[syllable]
phones.extend([ph + tone for ph in phone])
elif pinyin[-1].isalpha():
pass
else:
phones.extend(pinyin)
return phones
\ No newline at end of file
text/symbols.py 0 → 100644
View file @ b309ea1b
'''
Defines the set of symbols used in text input to the model.
'''
# japanese_cleaners
# _pad = '_'
# _punctuation = ',.!?-'
# _letters = 'AEINOQUabdefghijkmnoprstuvwyzʃʧ↓↑ '
'''# japanese_cleaners2
_pad = '_'
_punctuation = ',.!?-~…'
_letters = 'AEINOQUabdefghijkmnoprstuvwyzʃʧʦ↓↑ '
'''
'''# korean_cleaners
_pad = '_'
_punctuation = ',.!?…~'
_letters = 'ㄱㄴㄷㄹㅁㅂㅅㅇㅈㅊㅋㅌㅍㅎㄲㄸㅃㅆㅉㅏㅓㅗㅜㅡㅣㅐㅔ '
'''
'''# chinese_cleaners
_pad = '_'
_punctuation = '，。！？—…'
_letters = 'ㄅㄆㄇㄈㄉㄊㄋㄌㄍㄎㄏㄐㄑㄒㄓㄔㄕㄖㄗㄘㄙㄚㄛㄜㄝㄞㄟㄠㄡㄢㄣㄤㄥㄦㄧㄨㄩˉˊˇˋ˙ '
'''
# # zh_ja_mixture_cleaners
# _pad = '_'
# _punctuation = ',.!?-~…'
# _letters = 'AEINOQUabdefghijklmnoprstuvwyzʃʧʦɯɹəɥ⁼ʰ`→↓↑ '
'''# sanskrit_cleaners
_pad = '_'
_punctuation = '।'
_letters = 'ँंःअआइईउऊऋएऐओऔकखगघङचछजझञटठडढणतथदधनपफबभमयरलळवशषसहऽािीुूृॄेैोौ्ॠॢ '
'''
'''# cjks_cleaners
_pad = '_'
_punctuation = ',.!?-~…'
_letters = 'NQabdefghijklmnopstuvwxyzʃʧʥʦɯɹəɥçɸɾβŋɦː⁼ʰ`^#*=→↓↑ '
'''
'''# thai_cleaners
_pad = '_'
_punctuation = '.!? '
_letters = 'กขฃคฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรฤลวศษสหฬอฮฯะัาำิีึืุูเแโใไๅๆ็่้๊๋์'
'''
# # cjke_cleaners2
_pad = '_'
_punctuation = ',.!?-~…' + "'"
_IPA_letters = 'NQabdefghijklmnopstuvwxyzɑæʃʑçɯɪɔɛɹðəɫɥɸʊɾʒθβŋɦ⁼ʰ`^#*=ˈˌ→↓↑ '
_CNM3_letters = ['y1', 'y2', 'y3', 'y4', 'y5', 'n1', 'n2', 'n3', 'n4', 'n5', 'p1', 'p2', 'p3', 'p4', 'p5', 'x1', 'x2', 'x3', 'x4', 'x5', 'k1', 'k2', 'k3', 'k4', 'k5', 'l1', 'l2', 'l3', 'l4', 'l5', 'q1', 'q2', 'q3', 'q4', 'q5', 'w1', 'w2', 'w3', 'w4', 'w5', 'E1', 'E2', 'E3', 'E4', 'E5', 'b1', 'b2', 'b3', 'b4', 'b5', 'c1', 'c2', 'c3', 'c4', 'c5', 'z1', 'z2', 'z3', 'z4', 'z5', 'e1', 'e2', 'e3', 'e4', 'e5', 'f1', 'f2', 'f3', 'f4', 'f5', 's1', 's2', 's3', 's4', 's5', 'j1', 'j2', 'j3', 'j4', 'j5', 'o1', 'o2', 'o3', 'o4', 'o5', 'i1', 'i2', 'i3', 'i4', 'i5', 'd1', 'd2', 'd3', 'd4', 'd5', 'm1', 'm2', 'm3', 'm4', 'm5', 't1', 't2', 't3', 't4', 't5', 'h1', 'h2', 'h3', 'h4', 'h5', 'g1', 'g2', 'g3', 'g4', 'g5', 'v1', 'v2', 'v3', 'v4', 'v5', 'r1', 'r2', 'r3', 'r4', 'r5', 'a1', 'a2', 'a3', 'a4', 'a5', 'u1', 'u2', 'u3', 'u4', 'u5', 'I01', 'I02', 'I03', 'I04', 'I05', 'i01', 'i02', 'i03', 'i04', 'i05', 'uo1', 'uo2', 'uo3', 'uo4', 'uo5', 'o01', 'o02', 'o03', 'o04', 'o05', 'U01', 'U02', 'U03', 'U04', 'U05', 'v01', 'v02', 'v03', 'v04', 'v05', 'er1', 'er2', 'er3', 'er4', 'er5', 'A01', 'A02', 'A03', 'A04', 'A05', 'ai1', 'ai2', 'ai3', 'ai4', 'ai5', 'e01', 'e02', 'e03', 'e04', 'e05', 'sh1', 'sh2', 'sh3', 'sh4', 'sh5', 'an1', 'an2', 'an3', 'an4', 'an5', 'ou1', 'ou2', 'ou3', 'ou4', 'ou5', 'ch1', 'ch2', 'ch3', 'ch4', 'ch5', 'a01', 'a02', 'a03', 'a04', 'a05', 'N01', 'N02', 'N03', 'N04', 'N05', 'ao1', 'ao2', 'ao3', 'ao4', 'ao5', 've1', 've2', 've3', 've4', 've5', 'ir1', 'ir2', 'ir3', 'ir4', 'ir5', 'ng1', 'ng2', 'ng3', 'ng4', 'ng5', 'ua1', 'ua2', 'ua3', 'ua4', 'ua5', 'zh1', 'zh2', 'zh3', 'zh4', 'zh5', 'O01', 'O02', 'O03', 'O04', 'O05', 'ie1', 'ie2', 'ie3', 'ie4', 'ie5', 'E01', 'E02', 'E03', 'E04', 'E05', 'ia1', 'ia2', 'ia3', 'ia4', 'ia5', 'iE01', 'iE02', 'iE03', 'iE04', 'iE05', 'ang1', 'ang2', 'ang3', 'ang4', 'ang5', 'ng01', 'ng02', 'ng03', 'ng04', 'ng05', 'io01', 'io02', 'io03', 'io04', 'io05', 'iA01', 'iA02', 'iA03', 'iA04', 'iA05', 'uA01', 'uA02', 'uA03', 'uA04', 'uA05', 'ong1', 'ong2', 'ong3', 'ong4', 'ong5', 'oo01', 'oo02', 'oo03', 'oo04', 'oo05', 'uE01', 'uE02', 'uE03', 'uE04', 'uE05', 'vE01', 'vE02', 'vE03', 'vE04', 'vE05', 'ue01', 'ue02', 'ue03', 'ue04', 'ue05', 'ua01', 'ua02', 'ua03', 'ua04', 'ua05', 'iO01', 'iO02', 'iO03', 'iO04', 'iO05']
_additional = ['<sil>', '<asp>']
# _CNM3_letters = []
'''# shanghainese_cleaners
_pad = '_'
_punctuation = ',.!?…'
_letters = 'abdfghiklmnopstuvyzøŋȵɑɔɕəɤɦɪɿʑʔʰ̩̃ᴀᴇ15678 '
'''
'''# chinese_dialect_cleaners
_pad = '_'
_punctuation = ',.!?~…─'
_letters = '#Nabdefghijklmnoprstuvwxyzæçøŋœȵɐɑɒɓɔɕɗɘəɚɛɜɣɤɦɪɭɯɵɷɸɻɾɿʂʅʊʋʌʏʑʔʦʮʰʷˀː˥˦˧˨˩̥̩̃̚ᴀᴇ↑↓∅ⱼ '
'''
# Export all symbols:
symbols = [_pad] + list(_punctuation) + list(_IPA_letters) + _CNM3_letters + _additional
# Special symbol ids
SPACE_ID = symbols.index(" ")
train.py 0 → 100644
View file @ b309ea1b
import os
# os.environ['CUDA_VISIBLE_DEVICES'] = '0,1'
import torch
import torch.nn as nn
import torch.optim as optim
import torch.distributed as dist
from torch.nn.parallel import DistributedDataParallel as DDP
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from dataclasses import asdict
from tqdm import tqdm
from models.model import StableTTS
from datas.dataset import StableDataset, collate_fn
from datas.sampler import DistributedBucketSampler
from text import symbols
from config import MelConfig, ModelConfig, TrainConfig
from utils.scheduler import get_cosine_schedule_with_warmup
from utils.load import continue_training
from utils.plot import plot_alignment_to_numpy
torch.backends.cudnn.benchmark = True
def setup(rank, world_size):
os.environ['MASTER_ADDR'] = 'localhost'
os.environ['MASTER_PORT'] = '12356'
dist.init_process_group("gloo" if os.name == "nt" else "nccl", rank=rank, world_size=world_size)
def cleanup():
dist.destroy_process_group()
def _init_config(model_config: ModelConfig, mel_config: MelConfig, train_config: TrainConfig):
if not os.path.exists(train_config.model_save_path):
print(f'Creating {train_config.model_save_path}')
os.makedirs(train_config.model_save_path, exist_ok=True)
def train(rank, world_size):
setup(rank, world_size)
torch.cuda.set_device(rank)
model_config = ModelConfig()
mel_config = MelConfig()
train_config = TrainConfig()
_init_config(model_config, mel_config, train_config)
model = StableTTS(len(symbols), mel_config.n_mels, **asdict(model_config)).to(rank)
model = DDP(model, device_ids=[rank])
train_dataset = StableDataset(train_config.train_dataset_path, mel_config.hop_length)
train_sampler = DistributedBucketSampler(train_dataset, train_config.batch_size, [32,300,400,500,600,700,800,900,1000], num_replicas=world_size, rank=rank)
train_dataloader = DataLoader(train_dataset, batch_sampler=train_sampler, num_workers=4, pin_memory=True, collate_fn=collate_fn, persistent_workers=True)
if rank == 0:
writer = SummaryWriter(train_config.log_dir)
optimizer = optim.AdamW(model.parameters(), lr=train_config.learning_rate)
scheduler = get_cosine_schedule_with_warmup(optimizer, num_warmup_steps=int(train_config.warmup_steps), num_training_steps=train_config.num_epochs * len(train_dataloader))
# load latest checkpoints if possible
current_epoch = continue_training(train_config.model_save_path, model, optimizer)
model.train()
for epoch in range(current_epoch, train_config.num_epochs): # loop over the train_dataset multiple times
train_dataloader.batch_sampler.set_epoch(epoch)
if rank == 0:
dataloader = tqdm(train_dataloader)
else:
dataloader = train_dataloader
for batch_idx, datas in enumerate(dataloader):
datas = [data.to(rank, non_blocking=True) for data in datas]
x, x_lengths, y, y_lengths = datas
optimizer.zero_grad()
dur_loss, diff_loss, prior_loss, attn = model(x, x_lengths, y, y_lengths)
loss = dur_loss + diff_loss + prior_loss
loss.backward()
optimizer.step()
scheduler.step()
if rank == 0 and batch_idx % train_config.log_interval == 0:
steps = epoch * len(dataloader) + batch_idx
writer.add_scalar("training/diff_loss", diff_loss.item(), steps)
writer.add_scalar("training/dur_loss", dur_loss.item(), steps)
writer.add_scalar("training/prior_loss", prior_loss.item(), steps)
writer.add_scalar("learning_rate/learning_rate", scheduler.get_last_lr()[0], steps)
# writer.add_image("training/attention", plot_alignment_to_numpy(attn[0,0].data.cpu().numpy()), steps, dataformats='HWC')
if rank == 0 and epoch % train_config.save_interval == 0:
torch.save(model.module.state_dict(), os.path.join(train_config.model_save_path, f'checkpoint_{epoch}.pt'))
torch.save(optimizer.state_dict(), os.path.join(train_config.model_save_path, f'optimizer_{epoch}.pt'))
print(f"Rank {rank}, Epoch {epoch}, Loss {loss.item()}")
cleanup()
torch.set_num_threads(1)
torch.set_num_interop_threads(1)
if __name__ == "__main__":
world_size = torch.cuda.device_count()
#print(world_size)
torch.multiprocessing.spawn(train, args=(world_size,), nprocs=world_size, join=True)
utils/audio.py 0 → 100644
View file @ b309ea1b
from dataclasses import dataclass, asdict
import torch
from torch import Tensor
import torch.nn as nn
import torchaudio
import torchaudio.transforms
from config import MelConfig
class LogMelSpectrogram(nn.Module):
def __init__(self, config: MelConfig):
super().__init__()
self.spec = torchaudio.transforms.MelSpectrogram(**asdict(config))
def forward(self, x: Tensor) -> Tensor:
return self.compress(self.spec(x))
def compress(self, x: Tensor) -> Tensor:
return torch.log(torch.clamp(x, min=1e-5))
def decompress(self, x: Tensor) -> Tensor:
return torch.exp(x)
def load_and_resample_audio(audio_path, target_sr, device='cpu') -> Tensor:
try:
y, sr = torchaudio.load(audio_path)
except Exception as e:
print(str(e))
return None
y.to(device)
# Convert to mono
if y.size(0) > 1:
y = y[0, :].unsqueeze(0) # shape: [2, time] -> [time] -> [1, time]
# resample audio to target sample_rate
if sr != target_sr:
y = torchaudio.functional.resample(y, sr, target_sr)
return y
\ No newline at end of file
utils/load.py 0 → 100644
View file @ b309ea1b
import os
import torch
import torch.nn as nn
import torch.optim as optim
from torch.nn.parallel import DistributedDataParallel as DDP
def continue_training(checkpoint_path, model: DDP, optimizer: optim.Optimizer) -> int:
"""load the latest checkpoints and optimizers"""
model_dict = {}
optimizer_dict = {}
# globt all the checkpoints in the directory
for file in os.listdir(checkpoint_path):
if file.endswith(".pt"):
name, epoch_str = file.rsplit('_', 1)
epoch = int(epoch_str.split('.')[0])
if name.startswith("checkpoint"):
model_dict[epoch] = file
elif name.startswith("optimizer"):
optimizer_dict[epoch] = file
# get the largest epoch
common_epochs = set(model_dict.keys()) & set(optimizer_dict.keys())
if common_epochs:
max_epoch = max(common_epochs)
model_path = os.path.join(checkpoint_path, model_dict[max_epoch])
optimizer_path = os.path.join(checkpoint_path, optimizer_dict[max_epoch])
# load model and optimizer
model.module.load_state_dict(torch.load(model_path, map_location='cpu'))
optimizer.load_state_dict(torch.load(optimizer_path, map_location='cpu'))
print(f'resume model and optimizer from {max_epoch} epoch')
return max_epoch + 1
else:
# load pretrained checkpoint
if model_dict:
model_path = os.path.join(checkpoint_path, model_dict[max(model_dict.keys())])
model.module.load_state_dict(torch.load(model_path, map_location='cpu'))
return 0
\ No newline at end of file
utils/plot.py 0 → 100644
View file @ b309ea1b
import os
import glob
import logging
import json
import numpy as np
import torch
import torchaudio
MATPLOTLIB_FLAG = False
def plot_alignment_to_numpy(alignment, info=None):
global MATPLOTLIB_FLAG
if not MATPLOTLIB_FLAG:
import matplotlib
matplotlib.use("Agg")
MATPLOTLIB_FLAG = True
mpl_logger = logging.getLogger('matplotlib')
mpl_logger.setLevel(logging.WARNING)
import matplotlib.pylab as plt
import numpy as np
fig, ax = plt.subplots(figsize=(6, 4))
im = ax.imshow(alignment.transpose(), aspect='auto', origin='lower',
interpolation='none')
fig.colorbar(im, ax=ax)
xlabel = 'Decoder timestep'
if info is not None:
xlabel += '\n\n' + info
plt.xlabel(xlabel)
plt.ylabel('Encoder timestep')
plt.tight_layout()
fig.canvas.draw()
data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
plt.close()
return data
\ No newline at end of file
utils/scheduler.py 0 → 100644
View file @ b309ea1b
# modified from transformers.optimization
import math
from functools import partial
import torch
from torch import nn
from torch.optim import Optimizer
from torch.optim.lr_scheduler import LambdaLR, ReduceLROnPlateau
def _get_constant_lambda(_=None):
return 1
def get_constant_schedule(optimizer: Optimizer, last_epoch: int = -1):
"""
Create a schedule with a constant learning rate, using the learning rate set in optimizer.
Args:
optimizer ([`~torch.optim.Optimizer`]):
The optimizer for which to schedule the learning rate.
last_epoch (`int`, *optional*, defaults to -1):
The index of the last epoch when resuming training.
Return:
`torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
"""
return LambdaLR(optimizer, _get_constant_lambda, last_epoch=last_epoch)
def get_reduce_on_plateau_schedule(optimizer: Optimizer, **kwargs):
"""
Create a schedule with a constant learning rate that decreases when a metric has stopped improving.
Args:
optimizer ([`~torch.optim.Optimizer`]):
The optimizer for which to schedule the learning rate.
kwargs (`dict`, *optional*):
Extra parameters to be passed to the scheduler. See `torch.optim.lr_scheduler.ReduceLROnPlateau`
for possible parameters.
Return:
`torch.optim.lr_scheduler.ReduceLROnPlateau` with the appropriate schedule.
"""
return ReduceLROnPlateau(optimizer, **kwargs)
def _get_constant_schedule_with_warmup_lr_lambda(current_step: int, *, num_warmup_steps: int):
if current_step < num_warmup_steps:
return float(current_step) / float(max(1.0, num_warmup_steps))
return 1.0
def get_constant_schedule_with_warmup(optimizer: Optimizer, num_warmup_steps: int, last_epoch: int = -1):
"""
Create a schedule with a constant learning rate preceded by a warmup period during which the learning rate
increases linearly between 0 and the initial lr set in the optimizer.
Args:
optimizer ([`~torch.optim.Optimizer`]):
The optimizer for which to schedule the learning rate.
num_warmup_steps (`int`):
The number of steps for the warmup phase.
last_epoch (`int`, *optional*, defaults to -1):
The index of the last epoch when resuming training.
Return:
`torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
"""
lr_lambda = partial(_get_constant_schedule_with_warmup_lr_lambda, num_warmup_steps=num_warmup_steps)
return LambdaLR(optimizer, lr_lambda, last_epoch=last_epoch)
def _get_linear_schedule_with_warmup_lr_lambda(current_step: int, *, num_warmup_steps: int, num_training_steps: int):
if current_step < num_warmup_steps:
return float(current_step) / float(max(1, num_warmup_steps))
return max(0.0, float(num_training_steps - current_step) / float(max(1, num_training_steps - num_warmup_steps)))
def get_linear_schedule_with_warmup(optimizer, num_warmup_steps, num_training_steps, last_epoch=-1):
"""
Create a schedule with a learning rate that decreases linearly from the initial lr set in the optimizer to 0, after
a warmup period during which it increases linearly from 0 to the initial lr set in the optimizer.
Args:
optimizer ([`~torch.optim.Optimizer`]):
The optimizer for which to schedule the learning rate.
num_warmup_steps (`int`):
The number of steps for the warmup phase.
num_training_steps (`int`):
The total number of training steps.
last_epoch (`int`, *optional*, defaults to -1):
The index of the last epoch when resuming training.
Return:
`torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
"""
lr_lambda = partial(
_get_linear_schedule_with_warmup_lr_lambda,
num_warmup_steps=num_warmup_steps,
num_training_steps=num_training_steps,
)
return LambdaLR(optimizer, lr_lambda, last_epoch)
def _get_cosine_schedule_with_warmup_lr_lambda(
current_step: int, *, num_warmup_steps: int, num_training_steps: int, num_cycles: float
):
if current_step < num_warmup_steps:
return float(current_step) / float(max(1, num_warmup_steps))
progress = float(current_step - num_warmup_steps) / float(max(1, num_training_steps - num_warmup_steps))
return max(0.0, 0.5 * (1.0 + math.cos(math.pi * float(num_cycles) * 2.0 * progress)))
def get_cosine_schedule_with_warmup(
optimizer: Optimizer, num_warmup_steps: int, num_training_steps: int, num_cycles: float = 0.5, last_epoch: int = -1
):
"""
Create a schedule with a learning rate that decreases following the values of the cosine function between the
initial lr set in the optimizer to 0, after a warmup period during which it increases linearly between 0 and the
initial lr set in the optimizer.
Args:
optimizer ([`~torch.optim.Optimizer`]):
The optimizer for which to schedule the learning rate.
num_warmup_steps (`int`):
The number of steps for the warmup phase.
num_training_steps (`int`):
The total number of training steps.
num_cycles (`float`, *optional*, defaults to 0.5):
The number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0
following a half-cosine).
last_epoch (`int`, *optional*, defaults to -1):
The index of the last epoch when resuming training.
Return:
`torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
"""
lr_lambda = partial(
_get_cosine_schedule_with_warmup_lr_lambda,
num_warmup_steps=num_warmup_steps,
num_training_steps=num_training_steps,
num_cycles=num_cycles,
)
return LambdaLR(optimizer, lr_lambda, last_epoch)
def _get_cosine_with_hard_restarts_schedule_with_warmup_lr_lambda(
current_step: int, *, num_warmup_steps: int, num_training_steps: int, num_cycles: int
):
if current_step < num_warmup_steps:
return float(current_step) / float(max(1, num_warmup_steps))
progress = float(current_step - num_warmup_steps) / float(max(1, num_training_steps - num_warmup_steps))
if progress >= 1.0:
return 0.0
return max(0.0, 0.5 * (1.0 + math.cos(math.pi * ((float(num_cycles) * progress) % 1.0))))
def get_cosine_with_hard_restarts_schedule_with_warmup(
optimizer: Optimizer, num_warmup_steps: int, num_training_steps: int, num_cycles: int = 1, last_epoch: int = -1
):
"""
Create a schedule with a learning rate that decreases following the values of the cosine function between the
initial lr set in the optimizer to 0, with several hard restarts, after a warmup period during which it increases
linearly between 0 and the initial lr set in the optimizer.
Args:
optimizer ([`~torch.optim.Optimizer`]):
The optimizer for which to schedule the learning rate.
num_warmup_steps (`int`):
The number of steps for the warmup phase.
num_training_steps (`int`):
The total number of training steps.
num_cycles (`int`, *optional*, defaults to 1):
The number of hard restarts to use.
last_epoch (`int`, *optional*, defaults to -1):
The index of the last epoch when resuming training.
Return:
`torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
"""
lr_lambda = partial(
_get_cosine_with_hard_restarts_schedule_with_warmup_lr_lambda,
num_warmup_steps=num_warmup_steps,
num_training_steps=num_training_steps,
num_cycles=num_cycles,
)
return LambdaLR(optimizer, lr_lambda, last_epoch)
def _get_polynomial_decay_schedule_with_warmup_lr_lambda(
current_step: int,
*,
num_warmup_steps: int,
num_training_steps: int,
lr_end: float,
power: float,
lr_init: int,
):
if current_step < num_warmup_steps:
return float(current_step) / float(max(1, num_warmup_steps))
elif current_step > num_training_steps:
return lr_end / lr_init # as LambdaLR multiplies by lr_init
else:
lr_range = lr_init - lr_end
decay_steps = num_training_steps - num_warmup_steps
pct_remaining = 1 - (current_step - num_warmup_steps) / decay_steps
decay = lr_range * pct_remaining**power + lr_end
return decay / lr_init # as LambdaLR multiplies by lr_init
def get_polynomial_decay_schedule_with_warmup(
optimizer, num_warmup_steps, num_training_steps, lr_end=1e-7, power=1.0, last_epoch=-1
):
"""
Create a schedule with a learning rate that decreases as a polynomial decay from the initial lr set in the
optimizer to end lr defined by *lr_end*, after a warmup period during which it increases linearly from 0 to the
initial lr set in the optimizer.
Args:
optimizer ([`~torch.optim.Optimizer`]):
The optimizer for which to schedule the learning rate.
num_warmup_steps (`int`):
The number of steps for the warmup phase.
num_training_steps (`int`):
The total number of training steps.
lr_end (`float`, *optional*, defaults to 1e-7):
The end LR.
power (`float`, *optional*, defaults to 1.0):
Power factor.
last_epoch (`int`, *optional*, defaults to -1):
The index of the last epoch when resuming training.
Note: *power* defaults to 1.0 as in the fairseq implementation, which in turn is based on the original BERT
implementation at
https://github.com/google-research/bert/blob/f39e881b169b9d53bea03d2d341b31707a6c052b/optimization.py#L37
Return:
`torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
"""
lr_init = optimizer.defaults["lr"]
if not (lr_init > lr_end):
raise ValueError(f"lr_end ({lr_end}) must be be smaller than initial lr ({lr_init})")
lr_lambda = partial(
_get_polynomial_decay_schedule_with_warmup_lr_lambda,
num_warmup_steps=num_warmup_steps,
num_training_steps=num_training_steps,
lr_end=lr_end,
power=power,
lr_init=lr_init,
)
return LambdaLR(optimizer, lr_lambda, last_epoch)
def _get_inverse_sqrt_schedule_lr_lambda(current_step: int, *, num_warmup_steps: int, timescale: int = None):
if current_step < num_warmup_steps:
return float(current_step) / float(max(1, num_warmup_steps))
shift = timescale - num_warmup_steps
decay = 1.0 / math.sqrt((current_step + shift) / timescale)
return decay
def get_inverse_sqrt_schedule(
optimizer: Optimizer, num_warmup_steps: int, timescale: int = None, last_epoch: int = -1
):
"""
Create a schedule with an inverse square-root learning rate, from the initial lr set in the optimizer, after a
warmup period which increases lr linearly from 0 to the initial lr set in the optimizer.
Args:
optimizer ([`~torch.optim.Optimizer`]):
The optimizer for which to schedule the learning rate.
num_warmup_steps (`int`):
The number of steps for the warmup phase.
timescale (`int`, *optional*, defaults to `num_warmup_steps`):
Time scale.
last_epoch (`int`, *optional*, defaults to -1):
The index of the last epoch when resuming training.
Return:
`torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
"""
# Note: this implementation is adapted from
# https://github.com/google-research/big_vision/blob/f071ce68852d56099437004fd70057597a95f6ef/big_vision/utils.py#L930
if timescale is None:
timescale = num_warmup_steps
lr_lambda = partial(_get_inverse_sqrt_schedule_lr_lambda, num_warmup_steps=num_warmup_steps, timescale=timescale)
return LambdaLR(optimizer, lr_lambda, last_epoch=last_epoch)
\ No newline at end of file
vocoder.pt 0 → 100644
View file @ b309ea1b
File added
vocos_pytorch/README.md 0 → 100644
View file @ b309ea1b
<div align="center">
# Vocos for StableTTS
Modified from the official implementation of [Vocos](https://github.com/gemelo-ai/vocos/tree/main).
</div>
## Introduction
Vocos is a fast neural vocoder designed to synthesize audio waveforms from acoustic features. Trained using a Generative Adversarial Network (GAN) objective, Vocos can generate waveforms in a single forward pass. Unlike other typical GAN-based vocoders, Vocos does not model audio samples in the time domain. Instead, it generates spectral coefficients, facilitating rapid audio reconstruction through inverse Fourier transform.
## Inference
For detailed inference instructions, please refer to `inference.ipynb`
## Training
Setting up and training your model with Vocos is straightforward. Follow these steps to get started:
### Preparing Your Data
1. **Configure Data Settings**: Update the `DataConfig` in `preprocess.py`. Specifically, adjust the audio_dir to point to your collection of audio files.
2. **Run Preprocessing**: Run `preprocess.py`. This script will search (glob) for all audio files in the specified directory, resample them to the target sample_rate (modifiable in config.py), and generate a file list for training.
### Start training
1. **Adjust Training Configuration**: Edit `TrainConfig` in `config.py` to specify the file list path and tweak training hyperparameters to your needs.
2. **Start the Training Process**: Launch `train.py` to begin training your model.
### Experiment with Configurations
Feel free to explore and modify settings in `config.py` to modify the hyperparameters of vocos!
## References
[Vocos](https://github.com/gemelo-ai/vocos/tree/main)
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment