Initial commit

eval_audio/whisper_normalizer/basic.py

+import re
+import unicodedata
+
+import regex
+
+# non-ASCII letters that are not separated by "NFKD" normalization
+ADDITIONAL_DIACRITICS = {
+    "œ": "oe",
+    "Œ": "OE",
+    "ø": "o",
+    "Ø": "O",
+    "æ": "ae",
+    "Æ": "AE",
+    "ß": "ss",
+    "ẞ": "SS",
+    "đ": "d",
+    "Đ": "D",
+    "ð": "d",
+    "Ð": "D",
+    "þ": "th",
+    "Þ": "th",
+    "ł": "l",
+    "Ł": "L",
+}
+
+
+def remove_symbols_and_diacritics(s: str, keep=""):
+    """
+    Replace any other markers, symbols, and punctuations with a space,
+    and drop any diacritics (category 'Mn' and some manual mappings)
+    """
+    return "".join(
+        c
+        if c in keep
+        else ADDITIONAL_DIACRITICS[c]
+        if c in ADDITIONAL_DIACRITICS
+        else ""
+        if unicodedata.category(c) == "Mn"
+        else " "
+        if unicodedata.category(c)[0] in "MSP"
+        else c
+        for c in unicodedata.normalize("NFKD", s)
+    )
+
+
+def remove_symbols(s: str):
+    """
+    Replace any other markers, symbols, punctuations with a space, keeping diacritics
+    """
+    return "".join(
+        " " if unicodedata.category(c)[0] in "MSP" else c
+        for c in unicodedata.normalize("NFKC", s)
+    )
+
+
+class BasicTextNormalizer:
+    def __init__(self, remove_diacritics: bool = False, split_letters: bool = False):
+        self.clean = (
+            remove_symbols_and_diacritics if remove_diacritics else remove_symbols
+        )
+        self.split_letters = split_letters
+
+    def __call__(self, s: str):
+        s = s.lower()
+        s = re.sub(r"[<\[][^>\]]*[>\]]", "", s)  # remove words between brackets
+        s = re.sub(r"\(([^)]+?)\)", "", s)  # remove words between parenthesis
+        s = self.clean(s).lower()
+
+        if self.split_letters:
+            s = " ".join(regex.findall(r"\X", s, regex.U))
+
+        s = re.sub(
+            r"\s+", " ", s
+        )  # replace any successive whitespace characters with a space
+
+        return s

eval_audio/whisper_normalizer/english.json

+{
+    "accessorise": "accessorize",
+    "accessorised": "accessorized",
+    "accessorises": "accessorizes",
+    "accessorising": "accessorizing",
+    "acclimatisation": "acclimatization",
+    "acclimatise": "acclimatize",
+    "acclimatised": "acclimatized",
+    "acclimatises": "acclimatizes",
+    "acclimatising": "acclimatizing",
+    "accoutrements": "accouterments",
+    "aeon": "eon",
+    "aeons": "eons",
+    "aerogramme": "aerogram",
+    "aerogrammes": "aerograms",
+    "aeroplane": "airplane",
+    "aeroplanes": "airplanes",
+    "aesthete": "esthete",
+    "aesthetes": "esthetes",
+    "aesthetic": "esthetic",
+    "aesthetically": "esthetically",
+    "aesthetics": "esthetics",
+    "aetiology": "etiology",
+    "ageing": "aging",
+    "aggrandisement": "aggrandizement",
+    "agonise": "agonize",
+    "agonised": "agonized",
+    "agonises": "agonizes",
+    "agonising": "agonizing",
+    "agonisingly": "agonizingly",
+    "almanack": "almanac",
+    "almanacks": "almanacs",
+    "aluminium": "aluminum",
+    "amortisable": "amortizable",
+    "amortisation": "amortization",
+    "amortisations": "amortizations",
+    "amortise": "amortize",
+    "amortised": "amortized",
+    "amortises": "amortizes",
+    "amortising": "amortizing",
+    "amphitheatre": "amphitheater",
+    "amphitheatres": "amphitheaters",
+    "anaemia": "anemia",
+    "anaemic": "anemic",
+    "anaesthesia": "anesthesia",
+    "anaesthetic": "anesthetic",
+    "anaesthetics": "anesthetics",
+    "anaesthetise": "anesthetize",
+    "anaesthetised": "anesthetized",
+    "anaesthetises": "anesthetizes",
+    "anaesthetising": "anesthetizing",
+    "anaesthetist": "anesthetist",
+    "anaesthetists": "anesthetists",
+    "anaesthetize": "anesthetize",
+    "anaesthetized": "anesthetized",
+    "anaesthetizes": "anesthetizes",
+    "anaesthetizing": "anesthetizing",
+    "analogue": "analog",
+    "analogues": "analogs",
+    "analyse": "analyze",
+    "analysed": "analyzed",
+    "analyses": "analyzes",
+    "analysing": "analyzing",
+    "anglicise": "anglicize",
+    "anglicised": "anglicized",
+    "anglicises": "anglicizes",
+    "anglicising": "anglicizing",
+    "annualised": "annualized",
+    "antagonise": "antagonize",
+    "antagonised": "antagonized",
+    "antagonises": "antagonizes",
+    "antagonising": "antagonizing",
+    "apologise": "apologize",
+    "apologised": "apologized",
+    "apologises": "apologizes",
+    "apologising": "apologizing",
+    "appal": "appall",
+    "appals": "appalls",
+    "appetiser": "appetizer",
+    "appetisers": "appetizers",
+    "appetising": "appetizing",
+    "appetisingly": "appetizingly",
+    "arbour": "arbor",
+    "arbours": "arbors",
+    "archeological": "archaeological",
+    "archaeologically": "archeologically",
+    "archaeologist": "archeologist",
+    "archaeologists": "archeologists",
+    "archaeology": "archeology</span>",
+    "ardour": "ardor",
+    "armour": "armor",
+    "armoured": "armored",
+    "armourer": "armorer",
+    "armourers": "armorers",
+    "armouries": "armories",
+    "armoury": "armory",
+    "artefact": "artifact",
+    "artefacts": "artifacts",
+    "authorise": "authorize",
+    "authorised": "authorized",
+    "authorises": "authorizes",
+    "authorising": "authorizing",
+    "axe": "ax",
+    "backpedalled": "backpedaled",
+    "backpedalling": "backpedaling",
+    "bannister": "banister",
+    "bannisters": "banisters",
+    "baptise": "baptize",
+    "baptised": "baptized",
+    "baptises": "baptizes",
+    "baptising": "baptizing",
+    "bastardise": "bastardize",
+    "bastardised": "bastardized",
+    "bastardises": "bastardizes",
+    "bastardising": "bastardizing",
+    "battleax": "battleaxe",
+    "baulk": "balk",
+    "baulked": "balked",
+    "baulking": "balking",
+    "baulks": "balks",
+    "bedevilled": "bedeviled",
+    "bedevilling": "bedeviling",
+    "behaviour": "behavior",
+    "behavioural": "behavioral",
+    "behaviourism": "behaviorism",
+    "behaviourist": "behaviorist",
+    "behaviourists": "behaviorists",
+    "behaviours": "behaviors",
+    "behove": "behoove",
+    "behoved": "behooved",
+    "behoves": "behooves",
+    "bejewelled": "bejeweled",
+    "belabour": "belabor",
+    "belaboured": "belabored",
+    "belabouring": "belaboring",
+    "belabours": "belabors",
+    "bevelled": "beveled",
+    "bevvies": "bevies",
+    "bevvy": "bevy",
+    "biassed": "biased",
+    "biassing": "biasing",
+    "bingeing": "binging",
+    "bougainvillaea": "bougainvillea",
+    "bougainvillaeas": "bougainvilleas",
+    "bowdlerise": "bowdlerize",
+    "bowdlerised": "bowdlerized",
+    "bowdlerises": "bowdlerizes",
+    "bowdlerising": "bowdlerizing",
+    "breathalyse": "breathalyze",
+    "breathalysed": "breathalyzed",
+    "breathalyser": "breathalyzer",
+    "breathalysers": "breathalyzers",
+    "breathalyses": "breathalyzes",
+    "breathalysing": "breathalyzing",
+    "brutalise": "brutalize",
+    "brutalised": "brutalized",
+    "brutalises": "brutalizes",
+    "brutalising": "brutalizing",
+    "busses": "buses",
+    "bussing": "busing",
+    "caesarean": "cesarean",
+    "caesareans": "cesareans",
+    "calibre": "caliber",
+    "calibres": "calibers",
+    "calliper": "caliper",
+    "callipers": "calipers",
+    "callisthenics": "calisthenics",
+    "canalise": "canalize",
+    "canalised": "canalized",
+    "canalises": "canalizes",
+    "canalising": "canalizing",
+    "cancelation": "cancellation",
+    "cancelations": "cancellations",
+    "cancelled": "canceled",
+    "cancelling": "canceling",
+    "candour": "candor",
+    "cannibalise": "cannibalize",
+    "cannibalised": "cannibalized",
+    "cannibalises": "cannibalizes",
+    "cannibalising": "cannibalizing",
+    "canonise": "canonize",
+    "canonised": "canonized",
+    "canonises": "canonizes",
+    "canonising": "canonizing",
+    "capitalise": "capitalize",
+    "capitalised": "capitalized",
+    "capitalises": "capitalizes",
+    "capitalising": "capitalizing",
+    "caramelise": "caramelize",
+    "caramelised": "caramelized",
+    "caramelises": "caramelizes",
+    "caramelising": "caramelizing",
+    "carbonise": "carbonize",
+    "carbonised": "carbonized",
+    "carbonises": "carbonizes",
+    "carbonising": "carbonizing",
+    "carolled": "caroled",
+    "carolling": "caroling",
+    "catalogue": "catalog",
+    "catalogued": "cataloged",
+    "catalogues": "catalogs",
+    "cataloguing": "cataloging",
+    "catalyse": "catalyze",
+    "catalysed": "catalyzed",
+    "catalyses": "catalyzes",
+    "catalysing": "catalyzing",
+    "categorise": "categorize",
+    "categorised": "categorized",
+    "categorises": "categorizes",
+    "categorising": "categorizing",
+    "cauterise": "cauterize",
+    "cauterised": "cauterized",
+    "cauterises": "cauterizes",
+    "cauterising": "cauterizing",
+    "cavilled": "caviled",
+    "cavilling": "caviling",
+    "centigramme": "centigram",
+    "centigrammes": "centigrams",
+    "centilitre": "centiliter",
+    "centilitres": "centiliters",
+    "centimetre": "centimeter",
+    "centimetres": "centimeters",
+    "centralise": "centralize",
+    "centralised": "centralized",
+    "centralises": "centralizes",
+    "centralising": "centralizing",
+    "centre": "center",
+    "centred": "centered",
+    "centrefold": "centerfold",
+    "centrefolds": "centerfolds",
+    "centrepiece": "centerpiece",
+    "centrepieces": "centerpieces",
+    "centres": "centers",
+    "channelled": "channeled",
+    "channelling": "channeling",
+    "characterise": "characterize",
+    "characterised": "characterized",
+    "characterises": "characterizes",
+    "characterising": "characterizing",
+    "cheque": "check",
+    "chequebook": "checkbook",
+    "chequebooks": "checkbooks",
+    "chequered": "checkered",
+    "cheques": "checks",
+    "chilli": "chili",
+    "chimaera": "chimera",
+    "chimaeras": "chimeras",
+    "chiselled": "chiseled",
+    "chiselling": "chiseling",
+    "circularise": "circularize",
+    "circularised": "circularized",
+    "circularises": "circularizes",
+    "circularising": "circularizing",
+    "civilise": "civilize",
+    "civilised": "civilized",
+    "civilises": "civilizes",
+    "civilising": "civilizing",
+    "clamour": "clamor",
+    "clamoured": "clamored",
+    "clamouring": "clamoring",
+    "clamours": "clamors",
+    "clangour": "clangor",
+    "clarinettist": "clarinetist",
+    "clarinettists": "clarinetists",
+    "collectivise": "collectivize",
+    "collectivised": "collectivized",
+    "collectivises": "collectivizes",
+    "collectivising": "collectivizing",
+    "colonisation": "colonization",
+    "colonise": "colonize",
+    "colonised": "colonized",
+    "coloniser": "colonizer",
+    "colonisers": "colonizers",
+    "colonises": "colonizes",
+    "colonising": "colonizing",
+    "colour": "color",
+    "colourant": "colorant",
+    "colourants": "colorants",
+    "coloured": "colored",
+    "coloureds": "coloreds",
+    "colourful": "colorful",
+    "colourfully": "colorfully",
+    "colouring": "coloring",
+    "colourize": "colorize",
+    "colourized": "colorized",
+    "colourizes": "colorizes",
+    "colourizing": "colorizing",
+    "colourless": "colorless",
+    "colours": "colors",
+    "commercialise": "commercialize",
+    "commercialised": "commercialized",
+    "commercialises": "commercializes",
+    "commercialising": "commercializing",
+    "compartmentalise": "compartmentalize",
+    "compartmentalised": "compartmentalized",
+    "compartmentalises": "compartmentalizes",
+    "compartmentalising": "compartmentalizing",
+    "computerise": "computerize",
+    "computerised": "computerized",
+    "computerises": "computerizes",
+    "computerising": "computerizing",
+    "conceptualise": "conceptualize",
+    "conceptualised": "conceptualized",
+    "conceptualises": "conceptualizes",
+    "conceptualising": "conceptualizing",
+    "connexion": "connection",
+    "connexions": "connections",
+    "contextualise": "contextualize",
+    "contextualised": "contextualized",
+    "contextualises": "contextualizes",
+    "contextualising": "contextualizing",
+    "cosier": "cozier",
+    "cosies": "cozies",
+    "cosiest": "coziest",
+    "cosily": "cozily",
+    "cosiness": "coziness",
+    "cosy": "cozy",
+    "councillor": "councilor",
+    "councillors": "councilors",
+    "counselled": "counseled",
+    "counselling": "counseling",
+    "counsellor": "counselor",
+    "counsellors": "counselors",
+    "crenelated": "crenellated",
+    "criminalise": "criminalize",
+    "criminalised": "criminalized",
+    "criminalises": "criminalizes",
+    "criminalising": "criminalizing",
+    "criticise": "criticize",
+    "criticised": "criticized",
+    "criticises": "criticizes",
+    "criticising": "criticizing",
+    "crueller": "crueler",
+    "cruellest": "cruelest",
+    "crystallisation": "crystallization",
+    "crystallise": "crystallize",
+    "crystallised": "crystallized",
+    "crystallises": "crystallizes",
+    "crystallising": "crystallizing",
+    "cudgelled": "cudgeled",
+    "cudgelling": "cudgeling",
+    "customise": "customize",
+    "customised": "customized",
+    "customises": "customizes",
+    "customising": "customizing",
+    "cypher": "cipher",
+    "cyphers": "ciphers",
+    "decentralisation": "decentralization",
+    "decentralise": "decentralize",
+    "decentralised": "decentralized",
+    "decentralises": "decentralizes",
+    "decentralising": "decentralizing",
+    "decriminalisation": "decriminalization",
+    "decriminalise": "decriminalize",
+    "decriminalised": "decriminalized",
+    "decriminalises": "decriminalizes",
+    "decriminalising": "decriminalizing",
+    "defence": "defense",
+    "defenceless": "defenseless",
+    "defences": "defenses",
+    "dehumanisation": "dehumanization",
+    "dehumanise": "dehumanize",
+    "dehumanised": "dehumanized",
+    "dehumanises": "dehumanizes",
+    "dehumanising": "dehumanizing",
+    "demeanour": "demeanor",
+    "demilitarisation": "demilitarization",
+    "demilitarise": "demilitarize",
+    "demilitarised": "demilitarized",
+    "demilitarises": "demilitarizes",
+    "demilitarising": "demilitarizing",
+    "demobilisation": "demobilization",
+    "demobilise": "demobilize",
+    "demobilised": "demobilized",
+    "demobilises": "demobilizes",
+    "demobilising": "demobilizing",
+    "democratisation": "democratization",
+    "democratise": "democratize",
+    "democratised": "democratized",
+    "democratises": "democratizes",
+    "democratising": "democratizing",
+    "demonise": "demonize",
+    "demonised": "demonized",
+    "demonises": "demonizes",
+    "demonising": "demonizing",
+    "demoralisation": "demoralization",
+    "demoralise": "demoralize",
+    "demoralised": "demoralized",
+    "demoralises": "demoralizes",
+    "demoralising": "demoralizing",
+    "denationalisation": "denationalization",
+    "denationalise": "denationalize",
+    "denationalised": "denationalized",
+    "denationalises": "denationalizes",
+    "denationalising": "denationalizing",
+    "deodorise": "deodorize",
+    "deodorised": "deodorized",
+    "deodorises": "deodorizes",
+    "deodorising": "deodorizing",
+    "depersonalise": "depersonalize",
+    "depersonalised": "depersonalized",
+    "depersonalises": "depersonalizes",
+    "depersonalising": "depersonalizing",
+    "deputise": "deputize",
+    "deputised": "deputized",
+    "deputises": "deputizes",
+    "deputising": "deputizing",
+    "desensitisation": "desensitization",
+    "desensitise": "desensitize",
+    "desensitised": "desensitized",
+    "desensitises": "desensitizes",
+    "desensitising": "desensitizing",
+    "destabilisation": "destabilization",
+    "destabilise": "destabilize",
+    "destabilised": "destabilized",
+    "destabilises": "destabilizes",
+    "destabilising": "destabilizing",
+    "dialled": "dialed",
+    "dialling": "dialing",
+    "dialogue": "dialog",
+    "dialogues": "dialogs",
+    "diarrhoea": "diarrhea",
+    "digitise": "digitize",
+    "digitised": "digitized",
+    "digitises": "digitizes",
+    "digitising": "digitizing",
+    "disc": "disk",
+    "discolour": "discolor",
+    "discoloured": "discolored",
+    "discolouring": "discoloring",
+    "discolours": "discolors",
+    "discs": "disks",
+    "disembowelled": "disemboweled",
+    "disembowelling": "disemboweling",
+    "disfavour": "disfavor",
+    "dishevelled": "disheveled",
+    "dishonour": "dishonor",
+    "dishonourable": "dishonorable",
+    "dishonourably": "dishonorably",
+    "dishonoured": "dishonored",
+    "dishonouring": "dishonoring",
+    "dishonours": "dishonors",
+    "disorganisation": "disorganization",
+    "disorganised": "disorganized",
+    "distil": "distill",
+    "distils": "distills",
+    "dramatisation": "dramatization",
+    "dramatisations": "dramatizations",
+    "dramatise": "dramatize",
+    "dramatised": "dramatized",
+    "dramatises": "dramatizes",
+    "dramatising": "dramatizing",
+    "draught": "draft",
+    "draughtboard": "draftboard",
+    "draughtboards": "draftboards",
+    "draughtier": "draftier",
+    "draughtiest": "draftiest",
+    "draughts": "drafts",
+    "draughtsman": "draftsman",
+    "draughtsmanship": "draftsmanship",
+    "draughtsmen": "draftsmen",
+    "draughtswoman": "draftswoman",
+    "draughtswomen": "draftswomen",
+    "draughty": "drafty",
+    "drivelled": "driveled",
+    "drivelling": "driveling",
+    "duelled": "dueled",
+    "duelling": "dueling",
+    "economise": "economize",
+    "economised": "economized",
+    "economises": "economizes",
+    "economising": "economizing",
+    "edoema": "edema",
+    "editorialise": "editorialize",
+    "editorialised": "editorialized",
+    "editorialises": "editorializes",
+    "editorialising": "editorializing",
+    "empathise": "empathize",
+    "empathised": "empathized",
+    "empathises": "empathizes",
+    "empathising": "empathizing",
+    "emphasise": "emphasize",
+    "emphasised": "emphasized",
+    "emphasises": "emphasizes",
+    "emphasising": "emphasizing",
+    "enamelled": "enameled",
+    "enamelling": "enameling",
+    "enamoured": "enamored",
+    "encyclopaedia": "encyclopedia",
+    "encyclopaedias": "encyclopedias",
+    "encyclopaedic": "encyclopedic",
+    "endeavour": "endeavor",
+    "endeavoured": "endeavored",
+    "endeavouring": "endeavoring",
+    "endeavours": "endeavors",
+    "energise": "energize",
+    "energised": "energized",
+    "energises": "energizes",
+    "energising": "energizing",
+    "enrol": "enroll",
+    "enrols": "enrolls",
+    "enthral": "enthrall",
+    "enthrals": "enthralls",
+    "epaulette": "epaulet",
+    "epaulettes": "epaulets",
+    "epicentre": "epicenter",
+    "epicentres": "epicenters",
+    "epilogue": "epilog",
+    "epilogues": "epilogs",
+    "epitomise": "epitomize",
+    "epitomised": "epitomized",
+    "epitomises": "epitomizes",
+    "epitomising": "epitomizing",
+    "equalisation": "equalization",
+    "equalise": "equalize",
+    "equalised": "equalized",
+    "equaliser": "equalizer",
+    "equalisers": "equalizers",
+    "equalises": "equalizes",
+    "equalising": "equalizing",
+    "eulogise": "eulogize",
+    "eulogised": "eulogized",
+    "eulogises": "eulogizes",
+    "eulogising": "eulogizing",
+    "evangelise": "evangelize",
+    "evangelised": "evangelized",
+    "evangelises": "evangelizes",
+    "evangelising": "evangelizing",
+    "exorcise": "exorcize",
+    "exorcised": "exorcized",
+    "exorcises": "exorcizes",
+    "exorcising": "exorcizing",
+    "extemporisation": "extemporization",
+    "extemporise": "extemporize",
+    "extemporised": "extemporized",
+    "extemporises": "extemporizes",
+    "extemporising": "extemporizing",
+    "externalisation": "externalization",
+    "externalisations": "externalizations",
+    "externalise": "externalize",
+    "externalised": "externalized",
+    "externalises": "externalizes",
+    "externalising": "externalizing",
+    "factorise": "factorize",
+    "factorised": "factorized",
+    "factorises": "factorizes",
+    "factorising": "factorizing",
+    "faecal": "fecal",
+    "faeces": "feces",
+    "familiarisation": "familiarization",
+    "familiarise": "familiarize",
+    "familiarised": "familiarized",
+    "familiarises": "familiarizes",
+    "familiarising": "familiarizing",
+    "fantasise": "fantasize",
+    "fantasised": "fantasized",
+    "fantasises": "fantasizes",
+    "fantasising": "fantasizing",
+    "favour": "favor",
+    "favourable": "favorable",
+    "favourably": "favorably",
+    "favoured": "favored",
+    "favouring": "favoring",
+    "favourite": "favorite",
+    "favourites": "favorites",
+    "favouritism": "favoritism",
+    "favours": "favors",
+    "feminise": "feminize",
+    "feminised": "feminized",
+    "feminises": "feminizes",
+    "feminising": "feminizing",
+    "fertilisation": "fertilization",
+    "fertilise": "fertilize",
+    "fertilised": "fertilized",
+    "fertiliser": "fertilizer",
+    "fertilisers": "fertilizers",
+    "fertilises": "fertilizes",
+    "fertilising": "fertilizing",
+    "fervour": "fervor",
+    "fibre": "fiber",
+    "fibreglass": "fiberglass",
+    "fibres": "fibers",
+    "fictionalisation": "fictionalization",
+    "fictionalisations": "fictionalizations",
+    "fictionalise": "fictionalize",
+    "fictionalised": "fictionalized",
+    "fictionalises": "fictionalizes",
+    "fictionalising": "fictionalizing",
+    "fillet": "filet",
+    "filleted": "fileted",
+    "filleting": "fileting",
+    "fillets": "filets",
+    "finalisation": "finalization",
+    "finalise": "finalize",
+    "finalised": "finalized",
+    "finalises": "finalizes",
+    "finalising": "finalizing",
+    "flautist": "flutist",
+    "flautists": "flutists",
+    "flavour": "flavor",
+    "flavoured": "flavored",
+    "flavouring": "flavoring",
+    "flavourings": "flavorings",
+    "flavourless": "flavorless",
+    "flavours": "flavors",
+    "flavoursome": "flavorsome",
+    "flyer / flier": "flier / flyer",
+    "foetal": "fetal",
+    "foetid": "fetid",
+    "foetus": "fetus",
+    "foetuses": "fetuses",
+    "formalisation": "formalization",
+    "formalise": "formalize",
+    "formalised": "formalized",
+    "formalises": "formalizes",
+    "formalising": "formalizing",
+    "fossilisation": "fossilization",
+    "fossilise": "fossilize",
+    "fossilised": "fossilized",
+    "fossilises": "fossilizes",
+    "fossilising": "fossilizing",
+    "fraternisation": "fraternization",
+    "fraternise": "fraternize",
+    "fraternised": "fraternized",
+    "fraternises": "fraternizes",
+    "fraternising": "fraternizing",
+    "fulfil": "fulfill",
+    "fulfilment": "fulfillment",
+    "fulfils": "fulfills",
+    "funnelled": "funneled",
+    "funnelling": "funneling",
+    "galvanise": "galvanize",
+    "galvanised": "galvanized",
+    "galvanises": "galvanizes",
+    "galvanising": "galvanizing",
+    "gambolled": "gamboled",
+    "gambolling": "gamboling",
+    "gaol": "jail",
+    "gaolbird": "jailbird",
+    "gaolbirds": "jailbirds",
+    "gaolbreak": "jailbreak",
+    "gaolbreaks": "jailbreaks",
+    "gaoled": "jailed",
+    "gaoler": "jailer",
+    "gaolers": "jailers",
+    "gaoling": "jailing",
+    "gaols": "jails",
+    "gasses": "gases",
+    "gage": "gauge",
+    "gaged": "gauged",
+    "gages": "gauges",
+    "gaging": "gauging",
+    "generalisation": "generalization",
+    "generalisations": "generalizations",
+    "generalise": "generalize",
+    "generalised": "generalized",
+    "generalises": "generalizes",
+    "generalising": "generalizing",
+    "ghettoise": "ghettoize",
+    "ghettoised": "ghettoized",
+    "ghettoises": "ghettoizes",
+    "ghettoising": "ghettoizing",
+    "gipsies": "gypsies",
+    "glamorise": "glamorize",
+    "glamorised": "glamorized",
+    "glamorises": "glamorizes",
+    "glamorising": "glamorizing",
+    "glamor": "glamour",
+    "globalisation": "globalization",
+    "globalise": "globalize",
+    "globalised": "globalized",
+    "globalises": "globalizes",
+    "globalising": "globalizing",
+    "glueing": "gluing",
+    "goitre": "goiter",
+    "goitres": "goiters",
+    "gonorrhoea": "gonorrhea",
+    "gramme": "gram",
+    "grammes": "grams",
+    "gravelled": "graveled",
+    "grey": "gray",
+    "greyed": "grayed",
+    "greying": "graying",
+    "greyish": "grayish",
+    "greyness": "grayness",
+    "greys": "grays",
+    "grovelled": "groveled",
+    "grovelling": "groveling",
+    "groyne": "groin",
+    "groynes": "groins",
+    "gruelling": "grueling",
+    "gruellingly": "gruelingly",
+    "gryphon": "griffin",
+    "gryphons": "griffins",
+    "gynaecological": "gynecological",
+    "gynaecologist": "gynecologist",
+    "gynaecologists": "gynecologists",
+    "gynaecology": "gynecology",
+    "haematological": "hematological",
+    "haematologist": "hematologist",
+    "haematologists": "hematologists",
+    "haematology": "hematology",
+    "haemoglobin": "hemoglobin",
+    "haemophilia": "hemophilia",
+    "haemophiliac": "hemophiliac",
+    "haemophiliacs": "hemophiliacs",
+    "haemorrhage": "hemorrhage",
+    "haemorrhaged": "hemorrhaged",
+    "haemorrhages": "hemorrhages",
+    "haemorrhaging": "hemorrhaging",
+    "haemorrhoids": "hemorrhoids",
+    "harbour": "harbor",
+    "harboured": "harbored",
+    "harbouring": "harboring",
+    "harbours": "harbors",
+    "harmonisation": "harmonization",
+    "harmonise": "harmonize",
+    "harmonised": "harmonized",
+    "harmonises": "harmonizes",
+    "harmonising": "harmonizing",
+    "homoeopath": "homeopath",
+    "homoeopathic": "homeopathic",
+    "homoeopaths": "homeopaths",
+    "homoeopathy": "homeopathy",
+    "homogenise": "homogenize",
+    "homogenised": "homogenized",
+    "homogenises": "homogenizes",
+    "homogenising": "homogenizing",
+    "honour": "honor",
+    "honourable": "honorable",
+    "honourably": "honorably",
+    "honoured": "honored",
+    "honouring": "honoring",
+    "honours": "honors",
+    "hospitalisation": "hospitalization",
+    "hospitalise": "hospitalize",
+    "hospitalised": "hospitalized",
+    "hospitalises": "hospitalizes",
+    "hospitalising": "hospitalizing",
+    "humanise": "humanize",
+    "humanised": "humanized",
+    "humanises": "humanizes",
+    "humanising": "humanizing",
+    "humour": "humor",
+    "humoured": "humored",
+    "humouring": "humoring",
+    "humourless": "humorless",
+    "humours": "humors",
+    "hybridise": "hybridize",
+    "hybridised": "hybridized",
+    "hybridises": "hybridizes",
+    "hybridising": "hybridizing",
+    "hypnotise": "hypnotize",
+    "hypnotised": "hypnotized",
+    "hypnotises": "hypnotizes",
+    "hypnotising": "hypnotizing",
+    "hypothesise": "hypothesize",
+    "hypothesised": "hypothesized",
+    "hypothesises": "hypothesizes",
+    "hypothesising": "hypothesizing",
+    "idealisation": "idealization",
+    "idealise": "idealize",
+    "idealised": "idealized",
+    "idealises": "idealizes",
+    "idealising": "idealizing",
+    "idolise": "idolize",
+    "idolised": "idolized",
+    "idolises": "idolizes",
+    "idolising": "idolizing",
+    "immobilisation": "immobilization",
+    "immobilise": "immobilize",
+    "immobilised": "immobilized",
+    "immobiliser": "immobilizer",
+    "immobilisers": "immobilizers",
+    "immobilises": "immobilizes",
+    "immobilising": "immobilizing",
+    "immortalise": "immortalize",
+    "immortalised": "immortalized",
+    "immortalises": "immortalizes",
+    "immortalising": "immortalizing",
+    "immunisation": "immunization",
+    "immunise": "immunize",
+    "immunised": "immunized",
+    "immunises": "immunizes",
+    "immunising": "immunizing",
+    "impanelled": "impaneled",
+    "impanelling": "impaneling",
+    "imperilled": "imperiled",
+    "imperilling": "imperiling",
+    "individualise": "individualize",
+    "individualised": "individualized",
+    "individualises": "individualizes",
+    "individualising": "individualizing",
+    "industrialise": "industrialize",
+    "industrialised": "industrialized",
+    "industrialises": "industrializes",
+    "industrialising": "industrializing",
+    "inflexion": "inflection",
+    "inflexions": "inflections",
+    "initialise": "initialize",
+    "initialised": "initialized",
+    "initialises": "initializes",
+    "initialising": "initializing",
+    "initialled": "initialed",
+    "initialling": "initialing",
+    "instal": "install",
+    "instalment": "installment",
+    "instalments": "installments",
+    "instals": "installs",
+    "instil": "instill",
+    "instils": "instills",
+    "institutionalisation": "institutionalization",
+    "institutionalise": "institutionalize",
+    "institutionalised": "institutionalized",
+    "institutionalises": "institutionalizes",
+    "institutionalising": "institutionalizing",
+    "intellectualise": "intellectualize",
+    "intellectualised": "intellectualized",
+    "intellectualises": "intellectualizes",
+    "intellectualising": "intellectualizing",
+    "internalisation": "internalization",
+    "internalise": "internalize",
+    "internalised": "internalized",
+    "internalises": "internalizes",
+    "internalising": "internalizing",
+    "internationalisation": "internationalization",
+    "internationalise": "internationalize",
+    "internationalised": "internationalized",
+    "internationalises": "internationalizes",
+    "internationalising": "internationalizing",
+    "ionisation": "ionization",
+    "ionise": "ionize",
+    "ionised": "ionized",
+    "ioniser": "ionizer",
+    "ionisers": "ionizers",
+    "ionises": "ionizes",
+    "ionising": "ionizing",
+    "italicise": "italicize",
+    "italicised": "italicized",
+    "italicises": "italicizes",
+    "italicising": "italicizing",
+    "itemise": "itemize",
+    "itemised": "itemized",
+    "itemises": "itemizes",
+    "itemising": "itemizing",
+    "jeopardise": "jeopardize",
+    "jeopardised": "jeopardized",
+    "jeopardises": "jeopardizes",
+    "jeopardising": "jeopardizing",
+    "jewelled": "jeweled",
+    "jeweller": "jeweler",
+    "jewellers": "jewelers",
+    "jewellery": "jewelry",
+    "judgement": "judgment",
+    "kilogramme": "kilogram",
+    "kilogrammes": "kilograms",
+    "kilometre": "kilometer",
+    "kilometres": "kilometers",
+    "labelled": "labeled",
+    "labelling": "labeling",
+    "labour": "labor",
+    "laboured": "labored",
+    "labourer": "laborer",
+    "labourers": "laborers",
+    "labouring": "laboring",
+    "labours": "labors",
+    "lacklustre": "lackluster",
+    "legalisation": "legalization",
+    "legalise": "legalize",
+    "legalised": "legalized",
+    "legalises": "legalizes",
+    "legalising": "legalizing",
+    "legitimise": "legitimize",
+    "legitimised": "legitimized",
+    "legitimises": "legitimizes",
+    "legitimising": "legitimizing",
+    "leukaemia": "leukemia",
+    "levelled": "leveled",
+    "leveller": "leveler",
+    "levellers": "levelers",
+    "levelling": "leveling",
+    "libelled": "libeled",
+    "libelling": "libeling",
+    "libellous": "libelous",
+    "liberalisation": "liberalization",
+    "liberalise": "liberalize",
+    "liberalised": "liberalized",
+    "liberalises": "liberalizes",
+    "liberalising": "liberalizing",
+    "licence": "license",
+    "licenced": "licensed",
+    "licences": "licenses",
+    "licencing": "licensing",
+    "likeable": "likable",
+    "lionisation": "lionization",
+    "lionise": "lionize",
+    "lionised": "lionized",
+    "lionises": "lionizes",
+    "lionising": "lionizing",
+    "liquidise": "liquidize",
+    "liquidised": "liquidized",
+    "liquidiser": "liquidizer",
+    "liquidisers": "liquidizers",
+    "liquidises": "liquidizes",
+    "liquidising": "liquidizing",
+    "litre": "liter",
+    "litres": "liters",
+    "localise": "localize",
+    "localised": "localized",
+    "localises": "localizes",
+    "localising": "localizing",
+    "louvre": "louver",
+    "louvred": "louvered",
+    "louvres": "louvers",
+    "lustre": "luster",
+    "magnetise": "magnetize",
+    "magnetised": "magnetized",
+    "magnetises": "magnetizes",
+    "magnetising": "magnetizing",
+    "manoeuvrability": "maneuverability",
+    "manoeuvrable": "maneuverable",
+    "manoeuvre": "maneuver",
+    "manoeuvred": "maneuvered",
+    "manoeuvres": "maneuvers",
+    "manoeuvring": "maneuvering",
+    "manoeuvrings": "maneuverings",
+    "marginalisation": "marginalization",
+    "marginalise": "marginalize",
+    "marginalised": "marginalized",
+    "marginalises": "marginalizes",
+    "marginalising": "marginalizing",
+    "marshalled": "marshaled",
+    "marshalling": "marshaling",
+    "marvelled": "marveled",
+    "marvelling": "marveling",
+    "marvellous": "marvelous",
+    "marvellously": "marvelously",
+    "materialisation": "materialization",
+    "materialise": "materialize",
+    "materialised": "materialized",
+    "materialises": "materializes",
+    "materialising": "materializing",
+    "maximisation": "maximization",
+    "maximise": "maximize",
+    "maximised": "maximized",
+    "maximises": "maximizes",
+    "maximising": "maximizing",
+    "meagre": "meager",
+    "mechanisation": "mechanization",
+    "mechanise": "mechanize",
+    "mechanised": "mechanized",
+    "mechanises": "mechanizes",
+    "mechanising": "mechanizing",
+    "mediaeval": "medieval",
+    "memorialise": "memorialize",
+    "memorialised": "memorialized",
+    "memorialises": "memorializes",
+    "memorialising": "memorializing",
+    "memorise": "memorize",
+    "memorised": "memorized",
+    "memorises": "memorizes",
+    "memorising": "memorizing",
+    "mesmerise": "mesmerize",
+    "mesmerised": "mesmerized",
+    "mesmerises": "mesmerizes",
+    "mesmerising": "mesmerizing",
+    "metabolise": "metabolize",
+    "metabolised": "metabolized",
+    "metabolises": "metabolizes",
+    "metabolising": "metabolizing",
+    "metre": "meter",
+    "metres": "meters",
+    "micrometre": "micrometer",
+    "micrometres": "micrometers",
+    "militarise": "militarize",
+    "militarised": "militarized",
+    "militarises": "militarizes",
+    "militarising": "militarizing",
+    "milligramme": "milligram",
+    "milligrammes": "milligrams",
+    "millilitre": "milliliter",
+    "millilitres": "milliliters",
+    "millimetre": "millimeter",
+    "millimetres": "millimeters",
+    "miniaturisation": "miniaturization",
+    "miniaturise": "miniaturize",
+    "miniaturised": "miniaturized",
+    "miniaturises": "miniaturizes",
+    "miniaturising": "miniaturizing",
+    "minibusses": "minibuses",
+    "minimise": "minimize",
+    "minimised": "minimized",
+    "minimises": "minimizes",
+    "minimising": "minimizing",
+    "misbehaviour": "misbehavior",
+    "misdemeanour": "misdemeanor",
+    "misdemeanours": "misdemeanors",
+    "misspelt": "misspelled",
+    "mitre": "miter",
+    "mitres": "miters",
+    "mobilisation": "mobilization",
+    "mobilise": "mobilize",
+    "mobilised": "mobilized",
+    "mobilises": "mobilizes",
+    "mobilising": "mobilizing",
+    "modelled": "modeled",
+    "modeller": "modeler",
+    "modellers": "modelers",
+    "modelling": "modeling",
+    "modernise": "modernize",
+    "modernised": "modernized",
+    "modernises": "modernizes",
+    "modernising": "modernizing",
+    "moisturise": "moisturize",
+    "moisturised": "moisturized",
+    "moisturiser": "moisturizer",
+    "moisturisers": "moisturizers",
+    "moisturises": "moisturizes",
+    "moisturising": "moisturizing",
+    "monologue": "monolog",
+    "monologues": "monologs",
+    "monopolisation": "monopolization",
+    "monopolise": "monopolize",
+    "monopolised": "monopolized",
+    "monopolises": "monopolizes",
+    "monopolising": "monopolizing",
+    "moralise": "moralize",
+    "moralised": "moralized",
+    "moralises": "moralizes",
+    "moralising": "moralizing",
+    "motorised": "motorized",
+    "mould": "mold",
+    "moulded": "molded",
+    "moulder": "molder",
+    "mouldered": "moldered",
+    "mouldering": "moldering",
+    "moulders": "molders",
+    "mouldier": "moldier",
+    "mouldiest": "moldiest",
+    "moulding": "molding",
+    "mouldings": "moldings",
+    "moulds": "molds",
+    "mouldy": "moldy",
+    "moult": "molt",
+    "moulted": "molted",
+    "moulting": "molting",
+    "moults": "molts",
+    "moustache": "mustache",
+    "moustached": "mustached",
+    "moustaches": "mustaches",
+    "moustachioed": "mustachioed",
+    "multicoloured": "multicolored",
+    "nationalisation": "nationalization",
+    "nationalisations": "nationalizations",
+    "nationalise": "nationalize",
+    "nationalised": "nationalized",
+    "nationalises": "nationalizes",
+    "nationalising": "nationalizing",
+    "naturalisation": "naturalization",
+    "naturalise": "naturalize",
+    "naturalised": "naturalized",
+    "naturalises": "naturalizes",
+    "naturalising": "naturalizing",
+    "neighbour": "neighbor",
+    "neighbourhood": "neighborhood",
+    "neighbourhoods": "neighborhoods",
+    "neighbouring": "neighboring",
+    "neighbourliness": "neighborliness",
+    "neighbourly": "neighborly",
+    "neighbours": "neighbors",
+    "neutralisation": "neutralization",
+    "neutralise": "neutralize",
+    "neutralised": "neutralized",
+    "neutralises": "neutralizes",
+    "neutralising": "neutralizing",
+    "normalisation": "normalization",
+    "normalise": "normalize",
+    "normalised": "normalized",
+    "normalises": "normalizes",
+    "normalising": "normalizing",
+    "odour": "odor",
+    "odourless": "odorless",
+    "odours": "odors",
+    "oesophagus": "esophagus",
+    "oesophaguses": "esophaguses",
+    "oestrogen": "estrogen",
+    "offence": "offense",
+    "offences": "offenses",
+    "omelette": "omelet",
+    "omelettes": "omelets",
+    "optimise": "optimize",
+    "optimised": "optimized",
+    "optimises": "optimizes",
+    "optimising": "optimizing",
+    "organisation": "organization",
+    "organisational": "organizational",
+    "organisations": "organizations",
+    "organise": "organize",
+    "organised": "organized",
+    "organiser": "organizer",
+    "organisers": "organizers",
+    "organises": "organizes",
+    "organising": "organizing",
+    "orthopaedic": "orthopedic",
+    "orthopaedics": "orthopedics",
+    "ostracise": "ostracize",
+    "ostracised": "ostracized",
+    "ostracises": "ostracizes",
+    "ostracising": "ostracizing",
+    "outmanoeuvre": "outmaneuver",
+    "outmanoeuvred": "outmaneuvered",
+    "outmanoeuvres": "outmaneuvers",
+    "outmanoeuvring": "outmaneuvering",
+    "overemphasise": "overemphasize",
+    "overemphasised": "overemphasized",
+    "overemphasises": "overemphasizes",
+    "overemphasising": "overemphasizing",
+    "oxidisation": "oxidization",
+    "oxidise": "oxidize",
+    "oxidised": "oxidized",
+    "oxidises": "oxidizes",
+    "oxidising": "oxidizing",
+    "paederast": "pederast",
+    "paederasts": "pederasts",
+    "paediatric": "pediatric",
+    "paediatrician": "pediatrician",
+    "paediatricians": "pediatricians",
+    "paediatrics": "pediatrics",
+    "paedophile": "pedophile",
+    "paedophiles": "pedophiles",
+    "paedophilia": "pedophilia",
+    "palaeolithic": "paleolithic",
+    "palaeontologist": "paleontologist",
+    "palaeontologists": "paleontologists",
+    "palaeontology": "paleontology",
+    "panelled": "paneled",
+    "panelling": "paneling",
+    "panellist": "panelist",
+    "panellists": "panelists",
+    "paralyse": "paralyze",
+    "paralysed": "paralyzed",
+    "paralyses": "paralyzes",
+    "paralysing": "paralyzing",
+    "parcelled": "parceled",
+    "parcelling": "parceling",
+    "parlour": "parlor",
+    "parlours": "parlors",
+    "particularise": "particularize",
+    "particularised": "particularized",
+    "particularises": "particularizes",
+    "particularising": "particularizing",
+    "passivisation": "passivization",
+    "passivise": "passivize",
+    "passivised": "passivized",
+    "passivises": "passivizes",
+    "passivising": "passivizing",
+    "pasteurisation": "pasteurization",
+    "pasteurise": "pasteurize",
+    "pasteurised": "pasteurized",
+    "pasteurises": "pasteurizes",
+    "pasteurising": "pasteurizing",
+    "patronise": "patronize",
+    "patronised": "patronized",
+    "patronises": "patronizes",
+    "patronising": "patronizing",
+    "patronisingly": "patronizingly",
+    "pedalled": "pedaled",
+    "pedalling": "pedaling",
+    "pedestrianisation": "pedestrianization",
+    "pedestrianise": "pedestrianize",
+    "pedestrianised": "pedestrianized",
+    "pedestrianises": "pedestrianizes",
+    "pedestrianising": "pedestrianizing",
+    "penalise": "penalize",
+    "penalised": "penalized",
+    "penalises": "penalizes",
+    "penalising": "penalizing",
+    "pencilled": "penciled",
+    "pencilling": "penciling",
+    "personalise": "personalize",
+    "personalised": "personalized",
+    "personalises": "personalizes",
+    "personalising": "personalizing",
+    "pharmacopoeia": "pharmacopeia",
+    "pharmacopoeias": "pharmacopeias",
+    "philosophise": "philosophize",
+    "philosophised": "philosophized",
+    "philosophises": "philosophizes",
+    "philosophising": "philosophizing",
+    "philtre": "filter",
+    "philtres": "filters",
+    "phoney": "phony",
+    "plagiarise": "plagiarize",
+    "plagiarised": "plagiarized",
+    "plagiarises": "plagiarizes",
+    "plagiarising": "plagiarizing",
+    "plough": "plow",
+    "ploughed": "plowed",
+    "ploughing": "plowing",
+    "ploughman": "plowman",
+    "ploughmen": "plowmen",
+    "ploughs": "plows",
+    "ploughshare": "plowshare",
+    "ploughshares": "plowshares",
+    "polarisation": "polarization",
+    "polarise": "polarize",
+    "polarised": "polarized",
+    "polarises": "polarizes",
+    "polarising": "polarizing",
+    "politicisation": "politicization",
+    "politicise": "politicize",
+    "politicised": "politicized",
+    "politicises": "politicizes",
+    "politicising": "politicizing",
+    "popularisation": "popularization",
+    "popularise": "popularize",
+    "popularised": "popularized",
+    "popularises": "popularizes",
+    "popularising": "popularizing",
+    "pouffe": "pouf",
+    "pouffes": "poufs",
+    "practise": "practice",
+    "practised": "practiced",
+    "practises": "practices",
+    "practising": "practicing",
+    "praesidium": "presidium",
+    "praesidiums": "presidiums",
+    "pressurisation": "pressurization",
+    "pressurise": "pressurize",
+    "pressurised": "pressurized",
+    "pressurises": "pressurizes",
+    "pressurising": "pressurizing",
+    "pretence": "pretense",
+    "pretences": "pretenses",
+    "primaeval": "primeval",
+    "prioritisation": "prioritization",
+    "prioritise": "prioritize",
+    "prioritised": "prioritized",
+    "prioritises": "prioritizes",
+    "prioritising": "prioritizing",
+    "privatisation": "privatization",
+    "privatisations": "privatizations",
+    "privatise": "privatize",
+    "privatised": "privatized",
+    "privatises": "privatizes",
+    "privatising": "privatizing",
+    "professionalisation": "professionalization",
+    "professionalise": "professionalize",
+    "professionalised": "professionalized",
+    "professionalises": "professionalizes",
+    "professionalising": "professionalizing",
+    "programme": "program",
+    "programmes": "programs",
+    "prologue": "prolog",
+    "prologues": "prologs",
+    "propagandise": "propagandize",
+    "propagandised": "propagandized",
+    "propagandises": "propagandizes",
+    "propagandising": "propagandizing",
+    "proselytise": "proselytize",
+    "proselytised": "proselytized",
+    "proselytiser": "proselytizer",
+    "proselytisers": "proselytizers",
+    "proselytises": "proselytizes",
+    "proselytising": "proselytizing",
+    "psychoanalyse": "psychoanalyze",
+    "psychoanalysed": "psychoanalyzed",
+    "psychoanalyses": "psychoanalyzes",
+    "psychoanalysing": "psychoanalyzing",
+    "publicise": "publicize",
+    "publicised": "publicized",
+    "publicises": "publicizes",
+    "publicising": "publicizing",
+    "pulverisation": "pulverization",
+    "pulverise": "pulverize",
+    "pulverised": "pulverized",
+    "pulverises": "pulverizes",
+    "pulverising": "pulverizing",
+    "pummelled": "pummel",
+    "pummelling": "pummeled",
+    "pyjama": "pajama",
+    "pyjamas": "pajamas",
+    "pzazz": "pizzazz",
+    "quarrelled": "quarreled",
+    "quarrelling": "quarreling",
+    "radicalise": "radicalize",
+    "radicalised": "radicalized",
+    "radicalises": "radicalizes",
+    "radicalising": "radicalizing",
+    "rancour": "rancor",
+    "randomise": "randomize",
+    "randomised": "randomized",
+    "randomises": "randomizes",
+    "randomising": "randomizing",
+    "rationalisation": "rationalization",
+    "rationalisations": "rationalizations",
+    "rationalise": "rationalize",
+    "rationalised": "rationalized",
+    "rationalises": "rationalizes",
+    "rationalising": "rationalizing",
+    "ravelled": "raveled",
+    "ravelling": "raveling",
+    "realisable": "realizable",
+    "realisation": "realization",
+    "realisations": "realizations",
+    "realise": "realize",
+    "realised": "realized",
+    "realises": "realizes",
+    "realising": "realizing",
+    "recognisable": "recognizable",
+    "recognisably": "recognizably",
+    "recognisance": "recognizance",
+    "recognise": "recognize",
+    "recognised": "recognized",
+    "recognises": "recognizes",
+    "recognising": "recognizing",
+    "reconnoitre": "reconnoiter",
+    "reconnoitred": "reconnoitered",
+    "reconnoitres": "reconnoiters",
+    "reconnoitring": "reconnoitering",
+    "refuelled": "refueled",
+    "refuelling": "refueling",
+    "regularisation": "regularization",
+    "regularise": "regularize",
+    "regularised": "regularized",
+    "regularises": "regularizes",
+    "regularising": "regularizing",
+    "remodelled": "remodeled",
+    "remodelling": "remodeling",
+    "remould": "remold",
+    "remoulded": "remolded",
+    "remoulding": "remolding",
+    "remoulds": "remolds",
+    "reorganisation": "reorganization",
+    "reorganisations": "reorganizations",
+    "reorganise": "reorganize",
+    "reorganised": "reorganized",
+    "reorganises": "reorganizes",
+    "reorganising": "reorganizing",
+    "revelled": "reveled",
+    "reveller": "reveler",
+    "revellers": "revelers",
+    "revelling": "reveling",
+    "revitalise": "revitalize",
+    "revitalised": "revitalized",
+    "revitalises": "revitalizes",
+    "revitalising": "revitalizing",
+    "revolutionise": "revolutionize",
+    "revolutionised": "revolutionized",
+    "revolutionises": "revolutionizes",
+    "revolutionising": "revolutionizing",
+    "rhapsodise": "rhapsodize",
+    "rhapsodised": "rhapsodized",
+    "rhapsodises": "rhapsodizes",
+    "rhapsodising": "rhapsodizing",
+    "rigour": "rigor",
+    "rigours": "rigors",
+    "ritualised": "ritualized",
+    "rivalled": "rivaled",
+    "rivalling": "rivaling",
+    "romanticise": "romanticize",
+    "romanticised": "romanticized",
+    "romanticises": "romanticizes",
+    "romanticising": "romanticizing",
+    "rumour": "rumor",
+    "rumoured": "rumored",
+    "rumours": "rumors",
+    "sabre": "saber",
+    "sabres": "sabers",
+    "saltpetre": "saltpeter",
+    "sanitise": "sanitize",
+    "sanitised": "sanitized",
+    "sanitises": "sanitizes",
+    "sanitising": "sanitizing",
+    "satirise": "satirize",
+    "satirised": "satirized",
+    "satirises": "satirizes",
+    "satirising": "satirizing",
+    "saviour": "savior",
+    "saviours": "saviors",
+    "savour": "savor",
+    "savoured": "savored",
+    "savouries": "savories",
+    "savouring": "savoring",
+    "savours": "savors",
+    "savoury": "savory",
+    "scandalise": "scandalize",
+    "scandalised": "scandalized",
+    "scandalises": "scandalizes",
+    "scandalising": "scandalizing",
+    "sceptic": "skeptic",
+    "sceptical": "skeptical",
+    "sceptically": "skeptically",
+    "scepticism": "skepticism",
+    "sceptics": "skeptics",
+    "sceptre": "scepter",
+    "sceptres": "scepters",
+    "scrutinise": "scrutinize",
+    "scrutinised": "scrutinized",
+    "scrutinises": "scrutinizes",
+    "scrutinising": "scrutinizing",
+    "secularisation": "secularization",
+    "secularise": "secularize",
+    "secularised": "secularized",
+    "secularises": "secularizes",
+    "secularising": "secularizing",
+    "sensationalise": "sensationalize",
+    "sensationalised": "sensationalized",
+    "sensationalises": "sensationalizes",
+    "sensationalising": "sensationalizing",
+    "sensitise": "sensitize",
+    "sensitised": "sensitized",
+    "sensitises": "sensitizes",
+    "sensitising": "sensitizing",
+    "sentimentalise": "sentimentalize",
+    "sentimentalised": "sentimentalized",
+    "sentimentalises": "sentimentalizes",
+    "sentimentalising": "sentimentalizing",
+    "sepulchre": "sepulcher",
+    "sepulchres": "sepulchers",
+    "serialisation": "serialization",
+    "serialisations": "serializations",
+    "serialise": "serialize",
+    "serialised": "serialized",
+    "serialises": "serializes",
+    "serialising": "serializing",
+    "sermonise": "sermonize",
+    "sermonised": "sermonized",
+    "sermonises": "sermonizes",
+    "sermonising": "sermonizing",
+    "sheikh": "sheik",
+    "shovelled": "shoveled",
+    "shovelling": "shoveling",
+    "shrivelled": "shriveled",
+    "shrivelling": "shriveling",
+    "signalise": "signalize",
+    "signalised": "signalized",
+    "signalises": "signalizes",
+    "signalising": "signalizing",
+    "signalled": "signaled",
+    "signalling": "signaling",
+    "smoulder": "smolder",
+    "smouldered": "smoldered",
+    "smouldering": "smoldering",
+    "smoulders": "smolders",
+    "snivelled": "sniveled",
+    "snivelling": "sniveling",
+    "snorkelled": "snorkeled",
+    "snorkelling": "snorkeling",
+    "snowplough": "snowplow",
+    "snowploughs": "snowplow",
+    "socialisation": "socialization",
+    "socialise": "socialize",
+    "socialised": "socialized",
+    "socialises": "socializes",
+    "socialising": "socializing",
+    "sodomise": "sodomize",
+    "sodomised": "sodomized",
+    "sodomises": "sodomizes",
+    "sodomising": "sodomizing",
+    "solemnise": "solemnize",
+    "solemnised": "solemnized",
+    "solemnises": "solemnizes",
+    "solemnising": "solemnizing",
+    "sombre": "somber",
+    "specialisation": "specialization",
+    "specialisations": "specializations",
+    "specialise": "specialize",
+    "specialised": "specialized",
+    "specialises": "specializes",
+    "specialising": "specializing",
+    "spectre": "specter",
+    "spectres": "specters",
+    "spiralled": "spiraled",
+    "spiralling": "spiraling",
+    "splendour": "splendor",
+    "splendours": "splendors",
+    "squirrelled": "squirreled",
+    "squirrelling": "squirreling",
+    "stabilisation": "stabilization",
+    "stabilise": "stabilize",
+    "stabilised": "stabilized",
+    "stabiliser": "stabilizer",
+    "stabilisers": "stabilizers",
+    "stabilises": "stabilizes",
+    "stabilising": "stabilizing",
+    "standardisation": "standardization",
+    "standardise": "standardize",
+    "standardised": "standardized",
+    "standardises": "standardizes",
+    "standardising": "standardizing",
+    "stencilled": "stenciled",
+    "stencilling": "stenciling",
+    "sterilisation": "sterilization",
+    "sterilisations": "sterilizations",
+    "sterilise": "sterilize",
+    "sterilised": "sterilized",
+    "steriliser": "sterilizer",
+    "sterilisers": "sterilizers",
+    "sterilises": "sterilizes",
+    "sterilising": "sterilizing",
+    "stigmatisation": "stigmatization",
+    "stigmatise": "stigmatize",
+    "stigmatised": "stigmatized",
+    "stigmatises": "stigmatizes",
+    "stigmatising": "stigmatizing",
+    "storey": "story",
+    "storeys": "stories",
+    "subsidisation": "subsidization",
+    "subsidise": "subsidize",
+    "subsidised": "subsidized",
+    "subsidiser": "subsidizer",
+    "subsidisers": "subsidizers",
+    "subsidises": "subsidizes",
+    "subsidising": "subsidizing",
+    "succour": "succor",
+    "succoured": "succored",
+    "succouring": "succoring",
+    "succours": "succors",
+    "sulphate": "sulfate",
+    "sulphates": "sulfates",
+    "sulphide": "sulfide",
+    "sulphides": "sulfides",
+    "sulphur": "sulfur",
+    "sulphurous": "sulfurous",
+    "summarise": "summarize",
+    "summarised": "summarized",
+    "summarises": "summarizes",
+    "summarising": "summarizing",
+    "swivelled": "swiveled",
+    "swivelling": "swiveling",
+    "symbolise": "symbolize",
+    "symbolised": "symbolized",
+    "symbolises": "symbolizes",
+    "symbolising": "symbolizing",
+    "sympathise": "sympathize",
+    "sympathised": "sympathized",
+    "sympathiser": "sympathizer",
+    "sympathisers": "sympathizers",
+    "sympathises": "sympathizes",
+    "sympathising": "sympathizing",
+    "synchronisation": "synchronization",
+    "synchronise": "synchronize",
+    "synchronised": "synchronized",
+    "synchronises": "synchronizes",
+    "synchronising": "synchronizing",
+    "synthesise": "synthesize",
+    "synthesised": "synthesized",
+    "synthesiser": "synthesizer",
+    "synthesisers": "synthesizers",
+    "synthesises": "synthesizes",
+    "synthesising": "synthesizing",
+    "syphon": "siphon",
+    "syphoned": "siphoned",
+    "syphoning": "siphoning",
+    "syphons": "siphons",
+    "systematisation": "systematization",
+    "systematise": "systematize",
+    "systematised": "systematized",
+    "systematises": "systematizes",
+    "systematising": "systematizing",
+    "tantalise": "tantalize",
+    "tantalised": "tantalized",
+    "tantalises": "tantalizes",
+    "tantalising": "tantalizing",
+    "tantalisingly": "tantalizingly",
+    "tasselled": "tasseled",
+    "technicolour": "technicolor",
+    "temporise": "temporize",
+    "temporised": "temporized",
+    "temporises": "temporizes",
+    "temporising": "temporizing",
+    "tenderise": "tenderize",
+    "tenderised": "tenderized",
+    "tenderises": "tenderizes",
+    "tenderising": "tenderizing",
+    "terrorise": "terrorize",
+    "terrorised": "terrorized",
+    "terrorises": "terrorizes",
+    "terrorising": "terrorizing",
+    "theatre": "theater",
+    "theatregoer": "theatergoer",
+    "theatregoers": "theatergoers",
+    "theatres": "theaters",
+    "theorise": "theorize",
+    "theorised": "theorized",
+    "theorises": "theorizes",
+    "theorising": "theorizing",
+    "tonne": "ton",
+    "tonnes": "tons",
+    "towelled": "toweled",
+    "towelling": "toweling",
+    "toxaemia": "toxemia",
+    "tranquillise": "tranquilize",
+    "tranquillised": "tranquilized",
+    "tranquilliser": "tranquilizer",
+    "tranquillisers": "tranquilizers",
+    "tranquillises": "tranquilizes",
+    "tranquillising": "tranquilizing",
+    "tranquillity": "tranquility",
+    "tranquillize": "tranquilize",
+    "tranquillized": "tranquilized",
+    "tranquillizer": "tranquilizer",
+    "tranquillizers": "tranquilizers",
+    "tranquillizes": "tranquilizes",
+    "tranquillizing": "tranquilizing",
+    "tranquilly": "tranquility",
+    "transistorised": "transistorized",
+    "traumatise": "traumatize",
+    "traumatised": "traumatized",
+    "traumatises": "traumatizes",
+    "traumatising": "traumatizing",
+    "travelled": "traveled",
+    "traveller": "traveler",
+    "travellers": "travelers",
+    "travelling": "traveling",
+    "travelog": "travelogue",
+    "travelogs": "travelogues",
+    "trialled": "trialed",
+    "trialling": "trialing",
+    "tricolour": "tricolor",
+    "tricolours": "tricolors",
+    "trivialise": "trivialize",
+    "trivialised": "trivialized",
+    "trivialises": "trivializes",
+    "trivialising": "trivializing",
+    "tumour": "tumor",
+    "tumours": "tumors",
+    "tunnelled": "tunneled",
+    "tunnelling": "tunneling",
+    "tyrannise": "tyrannize",
+    "tyrannised": "tyrannized",
+    "tyrannises": "tyrannizes",
+    "tyrannising": "tyrannizing",
+    "tyre": "tire",
+    "tyres": "tires",
+    "unauthorised": "unauthorized",
+    "uncivilised": "uncivilized",
+    "underutilised": "underutilized",
+    "unequalled": "unequaled",
+    "unfavourable": "unfavorable",
+    "unfavourably": "unfavorably",
+    "unionisation": "unionization",
+    "unionise": "unionize",
+    "unionised": "unionized",
+    "unionises": "unionizes",
+    "unionising": "unionizing",
+    "unorganised": "unorganized",
+    "unravelled": "unraveled",
+    "unravelling": "unraveling",
+    "unrecognisable": "unrecognizable",
+    "unrecognised": "unrecognized",
+    "unrivalled": "unrivaled",
+    "unsavoury": "unsavory",
+    "untrammelled": "untrammeled",
+    "urbanisation": "urbanization",
+    "urbanise": "urbanize",
+    "urbanised": "urbanized",
+    "urbanises": "urbanizes",
+    "urbanising": "urbanizing",
+    "utilisable": "utilizable",
+    "utilisation": "utilization",
+    "utilise": "utilize",
+    "utilised": "utilized",
+    "utilises": "utilizes",
+    "utilising": "utilizing",
+    "valour": "valor",
+    "vandalise": "vandalize",
+    "vandalised": "vandalized",
+    "vandalises": "vandalizes",
+    "vandalising": "vandalizing",
+    "vaporisation": "vaporization",
+    "vaporise": "vaporize",
+    "vaporised": "vaporized",
+    "vaporises": "vaporizes",
+    "vaporising": "vaporizing",
+    "vapour": "vapor",
+    "vapours": "vapors",
+    "verbalise": "verbalize",
+    "verbalised": "verbalized",
+    "verbalises": "verbalizes",
+    "verbalising": "verbalizing",
+    "victimisation": "victimization",
+    "victimise": "victimize",
+    "victimised": "victimized",
+    "victimises": "victimizes",
+    "victimising": "victimizing",
+    "videodisc": "videodisk",
+    "videodiscs": "videodisks",
+    "vigour": "vigor",
+    "visualisation": "visualization",
+    "visualisations": "visualizations",
+    "visualise": "visualize",
+    "visualised": "visualized",
+    "visualises": "visualizes",
+    "visualising": "visualizing",
+    "vocalisation": "vocalization",
+    "vocalisations": "vocalizations",
+    "vocalise": "vocalize",
+    "vocalised": "vocalized",
+    "vocalises": "vocalizes",
+    "vocalising": "vocalizing",
+    "vulcanised": "vulcanized",
+    "vulgarisation": "vulgarization",
+    "vulgarise": "vulgarize",
+    "vulgarised": "vulgarized",
+    "vulgarises": "vulgarizes",
+    "vulgarising": "vulgarizing",
+    "waggon": "wagon",
+    "waggons": "wagons",
+    "watercolour": "watercolor",
+    "watercolours": "watercolors",
+    "weaselled": "weaseled",
+    "weaselling": "weaseling",
+    "westernisation": "westernization",
+    "westernise": "westernize",
+    "westernised": "westernized",
+    "westernises": "westernizes",
+    "westernising": "westernizing",
+    "womanise": "womanize",
+    "womanised": "womanized",
+    "womaniser": "womanizer",
+    "womanisers": "womanizers",
+    "womanises": "womanizes",
+    "womanising": "womanizing",
+    "woollen": "woolen",
+    "woollens": "woolens",
+    "woollies": "woolies",
+    "woolly": "wooly",
+    "worshipped": "worshiped",
+    "worshipping": "worshiping",
+    "worshipper": "worshiper",
+    "yodelled": "yodeled",
+    "yodelling": "yodeling",
+    "yoghourt": "yogurt",
+    "yoghourts": "yogurts",
+    "yoghurt": "yogurt",
+    "yoghurts": "yogurts",
+    "mhm": "hmm",
+    "mmm": "hmm"
+}
\ No newline at end of file

eval_audio/whisper_normalizer/english.py

+import json
+import os
+import re
+from fractions import Fraction
+from typing import Iterator, List, Match, Optional, Union
+
+from more_itertools import windowed
+
+from .basic import remove_symbols_and_diacritics
+
+
+class EnglishNumberNormalizer:
+    """
+    Convert any spelled-out numbers into arabic numbers, while handling:
+
+    - remove any commas
+    - keep the suffixes such as: `1960s`, `274th`, `32nd`, etc.
+    - spell out currency symbols after the number. e.g. `$20 million` -> `20000000 dollars`
+    - spell out `one` and `ones`
+    - interpret successive single-digit numbers as nominal: `one oh one` -> `101`
+    """
+
+    def __init__(self):
+        super().__init__()
+
+        self.zeros = {"o", "oh", "zero"}
+        self.ones = {
+            name: i
+            for i, name in enumerate(
+                [
+                    "one",
+                    "two",
+                    "three",
+                    "four",
+                    "five",
+                    "six",
+                    "seven",
+                    "eight",
+                    "nine",
+                    "ten",
+                    "eleven",
+                    "twelve",
+                    "thirteen",
+                    "fourteen",
+                    "fifteen",
+                    "sixteen",
+                    "seventeen",
+                    "eighteen",
+                    "nineteen",
+                ],
+                start=1,
+            )
+        }
+        self.ones_plural = {
+            "sixes" if name == "six" else name + "s": (value, "s")
+            for name, value in self.ones.items()
+        }
+        self.ones_ordinal = {
+            "zeroth": (0, "th"),
+            "first": (1, "st"),
+            "second": (2, "nd"),
+            "third": (3, "rd"),
+            "fifth": (5, "th"),
+            "twelfth": (12, "th"),
+            **{
+                name + ("h" if name.endswith("t") else "th"): (value, "th")
+                for name, value in self.ones.items()
+                if value > 3 and value != 5 and value != 12
+            },
+        }
+        self.ones_suffixed = {**self.ones_plural, **self.ones_ordinal}
+
+        self.tens = {
+            "twenty": 20,
+            "thirty": 30,
+            "forty": 40,
+            "fifty": 50,
+            "sixty": 60,
+            "seventy": 70,
+            "eighty": 80,
+            "ninety": 90,
+        }
+        self.tens_plural = {
+            name.replace("y", "ies"): (value, "s") for name, value in self.tens.items()
+        }
+        self.tens_ordinal = {
+            name.replace("y", "ieth"): (value, "th")
+            for name, value in self.tens.items()
+        }
+        self.tens_suffixed = {**self.tens_plural, **self.tens_ordinal}
+
+        self.multipliers = {
+            "hundred": 100,
+            "thousand": 1_000,
+            "million": 1_000_000,
+            "billion": 1_000_000_000,
+            "trillion": 1_000_000_000_000,
+            "quadrillion": 1_000_000_000_000_000,
+            "quintillion": 1_000_000_000_000_000_000,
+            "sextillion": 1_000_000_000_000_000_000_000,
+            "septillion": 1_000_000_000_000_000_000_000_000,
+            "octillion": 1_000_000_000_000_000_000_000_000_000,
+            "nonillion": 1_000_000_000_000_000_000_000_000_000_000,
+            "decillion": 1_000_000_000_000_000_000_000_000_000_000_000,
+        }
+        self.multipliers_plural = {
+            name + "s": (value, "s") for name, value in self.multipliers.items()
+        }
+        self.multipliers_ordinal = {
+            name + "th": (value, "th") for name, value in self.multipliers.items()
+        }
+        self.multipliers_suffixed = {
+            **self.multipliers_plural,
+            **self.multipliers_ordinal,
+        }
+        self.decimals = {*self.ones, *self.tens, *self.zeros}
+
+        self.preceding_prefixers = {
+            "minus": "-",
+            "negative": "-",
+            "plus": "+",
+            "positive": "+",
+        }
+        self.following_prefixers = {
+            "pound": "£",
+            "pounds": "£",
+            "euro": "€",
+            "euros": "€",
+            "dollar": "$",
+            "dollars": "$",
+            "cent": "¢",
+            "cents": "¢",
+        }
+        self.prefixes = set(
+            list(self.preceding_prefixers.values())
+            + list(self.following_prefixers.values())
+        )
+        self.suffixers = {
+            "per": {"cent": "%"},
+            "percent": "%",
+        }
+        self.specials = {"and", "double", "triple", "point"}
+
+        self.words = set(
+            [
+                key
+                for mapping in [
+                    self.zeros,
+                    self.ones,
+                    self.ones_suffixed,
+                    self.tens,
+                    self.tens_suffixed,
+                    self.multipliers,
+                    self.multipliers_suffixed,
+                    self.preceding_prefixers,
+                    self.following_prefixers,
+                    self.suffixers,
+                    self.specials,
+                ]
+                for key in mapping
+            ]
+        )
+        self.literal_words = {"one", "ones"}
+
+    def process_words(self, words: List[str]) -> Iterator[str]:
+        prefix: Optional[str] = None
+        value: Optional[Union[str, int]] = None
+        skip = False
+
+        def to_fraction(s: str):
+            try:
+                return Fraction(s)
+            except ValueError:
+                return None
+
+        def output(result: Union[str, int]):
+            nonlocal prefix, value
+            result = str(result)
+            if prefix is not None:
+                result = prefix + result
+            value = None
+            prefix = None
+            return result
+
+        if len(words) == 0:
+            return
+
+        for prev, current, next in windowed([None] + words + [None], 3):
+            if skip:
+                skip = False
+                continue
+
+            next_is_numeric = next is not None and re.match(r"^\d+(\.\d+)?$", next)
+            has_prefix = current[0] in self.prefixes
+            current_without_prefix = current[1:] if has_prefix else current
+            if re.match(r"^\d+(\.\d+)?$", current_without_prefix):
+                # arabic numbers (potentially with signs and fractions)
+                f = to_fraction(current_without_prefix)
+                assert f is not None
+                if value is not None:
+                    if isinstance(value, str) and value.endswith("."):
+                        # concatenate decimals / ip address components
+                        value = str(value) + str(current)
+                        continue
+                    else:
+                        yield output(value)
+
+                prefix = current[0] if has_prefix else prefix
+                if f.denominator == 1:
+                    value = f.numerator  # store integers as int
+                else:
+                    value = current_without_prefix
+            elif current not in self.words:
+                # non-numeric words
+                if value is not None:
+                    yield output(value)
+                yield output(current)
+            elif current in self.zeros:
+                value = str(value or "") + "0"
+            elif current in self.ones:
+                ones = self.ones[current]
+
+                if value is None:
+                    value = ones
+                elif isinstance(value, str) or prev in self.ones:
+                    if (
+                        prev in self.tens and ones < 10
+                    ):  # replace the last zero with the digit
+                        assert value[-1] == "0"
+                        value = value[:-1] + str(ones)
+                    else:
+                        value = str(value) + str(ones)
+                elif ones < 10:
+                    if value % 10 == 0:
+                        value += ones
+                    else:
+                        value = str(value) + str(ones)
+                else:  # eleven to nineteen
+                    if value % 100 == 0:
+                        value += ones
+                    else:
+                        value = str(value) + str(ones)
+            elif current in self.ones_suffixed:
+                # ordinal or cardinal; yield the number right away
+                ones, suffix = self.ones_suffixed[current]
+                if value is None:
+                    yield output(str(ones) + suffix)
+                elif isinstance(value, str) or prev in self.ones:
+                    if prev in self.tens and ones < 10:
+                        assert value[-1] == "0"
+                        yield output(value[:-1] + str(ones) + suffix)
+                    else:
+                        yield output(str(value) + str(ones) + suffix)
+                elif ones < 10:
+                    if value % 10 == 0:
+                        yield output(str(value + ones) + suffix)
+                    else:
+                        yield output(str(value) + str(ones) + suffix)
+                else:  # eleven to nineteen
+                    if value % 100 == 0:
+                        yield output(str(value + ones) + suffix)
+                    else:
+                        yield output(str(value) + str(ones) + suffix)
+                value = None
+            elif current in self.tens:
+                tens = self.tens[current]
+                if value is None:
+                    value = tens
+                elif isinstance(value, str):
+                    value = str(value) + str(tens)
+                else:
+                    if value % 100 == 0:
+                        value += tens
+                    else:
+                        value = str(value) + str(tens)
+            elif current in self.tens_suffixed:
+                # ordinal or cardinal; yield the number right away
+                tens, suffix = self.tens_suffixed[current]
+                if value is None:
+                    yield output(str(tens) + suffix)
+                elif isinstance(value, str):
+                    yield output(str(value) + str(tens) + suffix)
+                else:
+                    if value % 100 == 0:
+                        yield output(str(value + tens) + suffix)
+                    else:
+                        yield output(str(value) + str(tens) + suffix)
+            elif current in self.multipliers:
+                multiplier = self.multipliers[current]
+                if value is None:
+                    value = multiplier
+                elif isinstance(value, str) or value == 0:
+                    f = to_fraction(value)
+                    p = f * multiplier if f is not None else None
+                    if f is not None and p.denominator == 1:
+                        value = p.numerator
+                    else:
+                        yield output(value)
+                        value = multiplier
+                else:
+                    before = value // 1000 * 1000
+                    residual = value % 1000
+                    value = before + residual * multiplier
+            elif current in self.multipliers_suffixed:
+                multiplier, suffix = self.multipliers_suffixed[current]
+                if value is None:
+                    yield output(str(multiplier) + suffix)
+                elif isinstance(value, str):
+                    f = to_fraction(value)
+                    p = f * multiplier if f is not None else None
+                    if f is not None and p.denominator == 1:
+                        yield output(str(p.numerator) + suffix)
+                    else:
+                        yield output(value)
+                        yield output(str(multiplier) + suffix)
+                else:  # int
+                    before = value // 1000 * 1000
+                    residual = value % 1000
+                    value = before + residual * multiplier
+                    yield output(str(value) + suffix)
+                value = None
+            elif current in self.preceding_prefixers:
+                # apply prefix (positive, minus, etc.) if it precedes a number
+                if value is not None:
+                    yield output(value)
+
+                if next in self.words or next_is_numeric:
+                    prefix = self.preceding_prefixers[current]
+                else:
+                    yield output(current)
+            elif current in self.following_prefixers:
+                # apply prefix (dollars, cents, etc.) only after a number
+                if value is not None:
+                    prefix = self.following_prefixers[current]
+                    yield output(value)
+                else:
+                    yield output(current)
+            elif current in self.suffixers:
+                # apply suffix symbols (percent -> '%')
+                if value is not None:
+                    suffix = self.suffixers[current]
+                    if isinstance(suffix, dict):
+                        if next in suffix:
+                            yield output(str(value) + suffix[next])
+                            skip = True
+                        else:
+                            yield output(value)
+                            yield output(current)
+                    else:
+                        yield output(str(value) + suffix)
+                else:
+                    yield output(current)
+            elif current in self.specials:
+                if next not in self.words and not next_is_numeric:
+                    # apply special handling only if the next word can be numeric
+                    if value is not None:
+                        yield output(value)
+                    yield output(current)
+                elif current == "and":
+                    # ignore "and" after hundreds, thousands, etc.
+                    if prev not in self.multipliers:
+                        if value is not None:
+                            yield output(value)
+                        yield output(current)
+                elif current == "double" or current == "triple":
+                    if next in self.ones or next in self.zeros:
+                        repeats = 2 if current == "double" else 3
+                        ones = self.ones.get(next, 0)
+                        value = str(value or "") + str(ones) * repeats
+                        skip = True
+                    else:
+                        if value is not None:
+                            yield output(value)
+                        yield output(current)
+                elif current == "point":
+                    if next in self.decimals or next_is_numeric:
+                        value = str(value or "") + "."
+                else:
+                    # should all have been covered at this point
+                    raise ValueError(f"Unexpected token: {current}")
+            else:
+                # all should have been covered at this point
+                raise ValueError(f"Unexpected token: {current}")
+
+        if value is not None:
+            yield output(value)
+
+    def preprocess(self, s: str):
+        # replace "<number> and a half" with "<number> point five"
+        results = []
+
+        segments = re.split(r"\band\s+a\s+half\b", s)
+        for i, segment in enumerate(segments):
+            if len(segment.strip()) == 0:
+                continue
+            if i == len(segments) - 1:
+                results.append(segment)
+            else:
+                results.append(segment)
+                last_word = segment.rsplit(maxsplit=2)[-1]
+                if last_word in self.decimals or last_word in self.multipliers:
+                    results.append("point five")
+                else:
+                    results.append("and a half")
+
+        s = " ".join(results)
+
+        # put a space at number/letter boundary
+        s = re.sub(r"([a-z])([0-9])", r"\1 \2", s)
+        s = re.sub(r"([0-9])([a-z])", r"\1 \2", s)
+
+        # but remove spaces which could be a suffix
+        s = re.sub(r"([0-9])\s+(st|nd|rd|th|s)\b", r"\1\2", s)
+
+        return s
+
+    def postprocess(self, s: str):
+        def combine_cents(m: Match):
+            try:
+                currency = m.group(1)
+                integer = m.group(2)
+                cents = int(m.group(3))
+                return f"{currency}{integer}.{cents:02d}"
+            except ValueError:
+                return m.string
+
+        def extract_cents(m: Match):
+            try:
+                return f"¢{int(m.group(1))}"
+            except ValueError:
+                return m.string
+
+        # apply currency postprocessing; "$2 and ¢7" -> "$2.07"
+        s = re.sub(r"([€£$])([0-9]+) (?:and )?¢([0-9]{1,2})\b", combine_cents, s)
+        s = re.sub(r"[€£$]0.([0-9]{1,2})\b", extract_cents, s)
+
+        # write "one(s)" instead of "1(s)", just for the readability
+        s = re.sub(r"\b1(s?)\b", r"one\1", s)
+
+        return s
+
+    def __call__(self, s: str):
+        s = self.preprocess(s)
+        s = " ".join(word for word in self.process_words(s.split()) if word is not None)
+        s = self.postprocess(s)
+
+        return s
+
+
+class EnglishSpellingNormalizer:
+    """
+    Applies British-American spelling mappings as listed in [1].
+
+    [1] https://www.tysto.com/uk-us-spelling-list.html
+    """
+
+    def __init__(self):
+        mapping_path = os.path.join(os.path.dirname(__file__), "english.json")
+        self.mapping = json.load(open(mapping_path))
+
+    def __call__(self, s: str):
+        return " ".join(self.mapping.get(word, word) for word in s.split())
+
+
+class EnglishTextNormalizer:
+    def __init__(self):
+        self.ignore_patterns = r"\b(hmm|mm|mhm|mmm|uh|um)\b"
+        self.replacers = {
+            # common contractions
+            r"\bwon't\b": "will not",
+            r"\bcan't\b": "can not",
+            r"\blet's\b": "let us",
+            r"\bain't\b": "aint",
+            r"\by'all\b": "you all",
+            r"\bwanna\b": "want to",
+            r"\bgotta\b": "got to",
+            r"\bgonna\b": "going to",
+            r"\bi'ma\b": "i am going to",
+            r"\bimma\b": "i am going to",
+            r"\bwoulda\b": "would have",
+            r"\bcoulda\b": "could have",
+            r"\bshoulda\b": "should have",
+            r"\bma'am\b": "madam",
+            # contractions in titles/prefixes
+            r"\bmr\b": "mister ",
+            r"\bmrs\b": "missus ",
+            r"\bst\b": "saint ",
+            r"\bdr\b": "doctor ",
+            r"\bprof\b": "professor ",
+            r"\bcapt\b": "captain ",
+            r"\bgov\b": "governor ",
+            r"\bald\b": "alderman ",
+            r"\bgen\b": "general ",
+            r"\bsen\b": "senator ",
+            r"\brep\b": "representative ",
+            r"\bpres\b": "president ",
+            r"\brev\b": "reverend ",
+            r"\bhon\b": "honorable ",
+            r"\basst\b": "assistant ",
+            r"\bassoc\b": "associate ",
+            r"\blt\b": "lieutenant ",
+            r"\bcol\b": "colonel ",
+            r"\bjr\b": "junior ",
+            r"\bsr\b": "senior ",
+            r"\besq\b": "esquire ",
+            # prefect tenses, ideally it should be any past participles, but it's harder..
+            r"'d been\b": " had been",
+            r"'s been\b": " has been",
+            r"'d gone\b": " had gone",
+            r"'s gone\b": " has gone",
+            r"'d done\b": " had done",  # "'s done" is ambiguous
+            r"'s got\b": " has got",
+            # general contractions
+            r"n't\b": " not",
+            r"'re\b": " are",
+            r"'s\b": " is",
+            r"'d\b": " would",
+            r"'ll\b": " will",
+            r"'t\b": " not",
+            r"'ve\b": " have",
+            r"'m\b": " am",
+        }
+        self.standardize_numbers = EnglishNumberNormalizer()
+        self.standardize_spellings = EnglishSpellingNormalizer()
+
+    def __call__(self, s: str):
+        s = s.lower()
+
+        s = re.sub(r"[<\[][^>\]]*[>\]]", "", s)  # remove words between brackets
+        s = re.sub(r"\(([^)]+?)\)", "", s)  # remove words between parenthesis
+        s = re.sub(self.ignore_patterns, "", s)
+        s = re.sub(r"\s+'", "'", s)  # when there's a space before an apostrophe
+
+        for pattern, replacement in self.replacers.items():
+            s = re.sub(pattern, replacement, s)
+
+        s = re.sub(r"(\d),(\d)", r"\1\2", s)  # remove commas between digits
+        s = re.sub(r"\.([^0-9]|$)", r" \1", s)  # remove periods not followed by numbers
+        s = remove_symbols_and_diacritics(s, keep=".%$¢€£")  # keep numeric symbols
+
+        s = self.standardize_numbers(s)
+        s = self.standardize_spellings(s)
+
+        # now remove prefix/suffix symbols that are not preceded/followed by numbers
+        s = re.sub(r"[.$¢€£]([^0-9])", r" \1", s)
+        s = re.sub(r"([^0-9])%", r"\1 ", s)
+
+        s = re.sub(r"\s+", " ", s)  # replace any successive whitespaces with a space
+
+        return s
\ No newline at end of file

finetune/accelerate_configs/deepspeed_z1.yaml

+compute_environment: LOCAL_MACHINE
+debug: false
+deepspeed_config:
+  deepspeed_multinode_launcher: standard
+  gradient_accumulation_steps: 1
+  gradient_clipping: 1.0
+  zero3_init_flag: false
+  zero_stage: 1
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_process_ip: localhost
+main_process_port: 9999
+main_training_function: main
+mixed_precision: bf16
+num_machines: 2
+num_processes: 16
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

finetune/accelerate_configs/deepspeed_z2.yaml

+compute_environment: LOCAL_MACHINE
+debug: false
+deepspeed_config:
+  deepspeed_multinode_launcher: standard
+  gradient_accumulation_steps: 1
+  gradient_clipping: 1.0
+  offload_optimizer_device: none
+  offload_param_device: none
+  zero3_init_flag: false
+  zero_stage: 2
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_process_ip: localhost
+main_process_port: 9999
+main_training_function: main
+mixed_precision: bf16
+num_machines: 2
+num_processes: 16
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

finetune/accelerate_configs/deepspeed_z3.yaml

+compute_environment: LOCAL_MACHINE                                                                                                                                                                     
+debug: false                                                                                                                                                                                           
+deepspeed_config:
+  deepspeed_multinode_launcher: standard
+  gradient_accumulation_steps: 1
+  gradient_clipping: 1.0
+  offload_optimizer_device: cpu
+  offload_param_device: cpu
+  zero3_init_flag: true
+  zero3_save_16bit_model: false
+  zero_stage: 3
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_process_ip: localhost
+main_process_port: 999
+main_training_function: main
+mixed_precision: bf16
+num_machines: 1
+num_processes: 8
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false
\ No newline at end of file

finetune/run.py

+import json
+import os
+import sys
+import math
+import random
+import logging
+import argparse
+import numpy as np
+from pathlib import Path
+from tqdm.auto import tqdm
+from collections import defaultdict
+
+import librosa
+from io import BytesIO
+from urllib.request import urlopen
+
+from peft import get_peft_model
+from peft import LoraConfig, TaskType
+
+import torch
+from torch.utils.data import DataLoader
+from datasets import IterableDataset
+
+from accelerate.utils import set_seed
+from accelerate.logging import get_logger
+from accelerate import Accelerator, DistributedType
+
+import transformers
+from transformers import (
+    AutoConfig,
+    AutoProcessor,
+    Qwen2AudioForConditionalGeneration,
+    SchedulerType,
+    get_scheduler,
+)
+
+
+logger = get_logger(__name__)
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model_name_or_path",
+        type=str,
+        default="qwen2-audio",
+        help="Path to pretrained model or model identifier from huggingface.co/models",
+    )
+    parser.add_argument(
+        "--output_dir",
+        type=str,
+        default="output",
+        help="The output directory where the model predictions and checkpoints will be written.",
+    )
+    parser.add_argument(
+        "--seed", type=int, default=42, help="Random seed"
+    )
+    parser.add_argument(
+        "--learning_rate", type=float, default=5e-5, help="The initial learning rate for AdamW."
+    )
+    parser.add_argument(
+        "--weight_decay", type=float, default=0.0, help="Weight decay for AdamW."
+    )
+    parser.add_argument(
+        "--per_device_train_batch_size",
+        type=int,
+        default=1,
+        help="Batch size per GPU/TPU core/CPU for training.",
+    )
+    parser.add_argument(
+        "--gradient_accumulation_steps",
+        type=int,
+        default=1,
+        help="Number of updates steps to accumulate before performing a backward/update pass.",
+    )
+    parser.add_argument(
+        "--steps_per_print",
+        type=int,
+        default=1,
+        help="Number of steps before printing the loss.",
+    )
+    parser.add_argument(
+        "--trust_remote_code",
+        action="store_true",
+        help="Trust remote code for the model and tokenizer.",
+    )
+    parser.add_argument(
+        "--low_cpu_mem_usage",
+        action="store_true",
+        help="Use low CPU memory usage for the model.",
+    )
+    parser.add_argument(
+        "--flash_attention",
+        action="store_true",
+        help="Use FlashAttention for the model.",
+    )
+    parser.add_argument(
+        "--max_train_steps",
+        type=int,
+        default=1000,
+        help="Total number of training steps to perform.",
+    )
+    parser.add_argument(
+        "--num_warmup_steps",
+        type=int,
+        default=0,
+        help="Number of steps for the warmup in the lr scheduler.",
+    )
+    parser.add_argument(
+        "--lr_scheduler_type",
+        type=SchedulerType,
+        default=SchedulerType.LINEAR,
+        help="The learning rate scheduler type to use.",
+    )
+    parser.add_argument(
+        "--save_interval",
+        type=int,
+        default=100,
+        help="Number of steps before saving the model.",
+    )
+    parser.add_argument(
+        "--gradient_checkpointing",
+        action="store_true",
+        help="Use gradient checkpointing to save memory.",
+    )
+    parser.add_argument(
+        "--lora",
+        action="store_true",
+        help="Use lora to finetune.",
+    )
+    return parser.parse_args()
+
+
+def toy_data():
+    conversation = [
+        {
+            "role": "system", "content": "You are a helpful assistant."
+        },
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "audio",
+                    "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/guess_age_gender.wav"
+                }
+            ]
+        },
+        {
+            "role": "assistant", "content": "Yes, the speaker is female and in her twenties."
+        },
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "audio",
+                    "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/translate_to_chinese.wav"
+                }
+            ]
+        }
+    ]
+    conversation1 = [
+        {
+            "role": "system", "content": "You are a helpful assistant."
+        },
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "audio",
+                    "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/glass-breaking-151256.mp3"
+                },
+                {
+                    "type": "text", "text": "What's that sound?"
+                },
+            ]
+        },
+        {
+            "role": "assistant", "content": "It is the sound of glass shattering."
+        },
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "What can you do when you hear that?"},
+            ]
+        },
+        {
+            "role": "assistant",
+            "content": "Stay alert and cautious, and check if anyone is hurt or if there is any damage to property."
+        },
+        {
+            "role": "user", "content": [
+                {
+                    "type": "audio",
+                    "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/1272-128104-0000.flac"
+                },
+                {"type": "text", "text": "What does the person say?"},
+            ]
+        }
+    ]
+    while True:
+        if random.random() < 0.5:
+            yield {"conversations": conversation}
+        else:
+            yield {"conversations": conversation1}
+
+
+def main(args):
+    # Initialize the accelerator. We will let the accelerator handle device placement for us in this example.
+    accelerator_log_kwargs = {"dispatch_batches": False}
+
+    accelerator = Accelerator(
+        gradient_accumulation_steps=args.gradient_accumulation_steps,
+        **accelerator_log_kwargs
+    )
+
+    def init_dataloader(processor):
+        def _func(batch):
+            # copy from `https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct`
+            conversations = batch["conversations"]
+
+            text = [
+                processor.apply_chat_template(
+                    conversation,
+                    add_generation_prompt=False,
+                    tokeni_in_conversationze=False
+                )
+                for conversation in conversations
+            ]
+
+            audios, audio_num_for_each_conversation = [], []
+            for conversation in conversations:
+                audio_num = 0
+                for message in conversation:
+                    if isinstance(message["content"], list):
+                        for ele in message["content"]:
+                            if ele["type"] == "audio":
+                                audios.append(
+                                    librosa.load(
+                                        BytesIO(
+                                            urlopen(ele['audio_url']).read()
+                                        ),
+                                        sr=processor.feature_extractor.sampling_rate)[0]
+                                )
+                                audio_num += 1
+                audio_num_for_each_conversation.append(audio_num)
+
+            inputs = processor(
+                text=text,
+                audios=audios if audios else None,
+                return_tensors="pt",
+                padding=True
+            )
+
+            # Split the tensors for each conversation, make sure the dataset is iterable
+            inputs["feature_attention_mask"] = [
+                x for x in torch.split(
+                    inputs["feature_attention_mask"],
+                    audio_num_for_each_conversation, dim=0)
+            ]
+            inputs["input_features"] = [
+                x for x in torch.split(
+                    inputs["input_features"],
+                    audio_num_for_each_conversation,
+                    dim=0
+                )
+            ]
+            logger.warning(
+                "We automatically learn from all tokens except for `audio` in the conversation. If you want to learn about a specific `role` or `content`, please modify the code accordingly."
+            )
+            # Qwen2AudioForConditionalGeneration will automatically shift the input_ids for you
+            inputs["labels"] = inputs["input_ids"]
+            return inputs
+
+        # Load dataset
+        dataset = IterableDataset.from_generator(toy_data)
+        dataset = dataset.map(
+            _func,
+            batched=True,
+            remove_columns=["conversations"],
+            batch_size=2
+        )
+
+        def collate_fn(batch):
+            flatten_batch = defaultdict(list)
+            for k in batch[0]:
+                for instance in batch:
+                    if isinstance(instance[k], list):
+                        flatten_batch[k] += instance[k]
+                    else:
+                        flatten_batch[k].append(instance[k])
+            return {
+                k: torch.cat(v, dim=0)
+                if k in ["feature_attention_mask", "input_features"] else torch.stack(v)
+                for k, v in flatten_batch.items()
+            }
+
+        dataloader = DataLoader(
+            dataset,
+            batch_size=args.per_device_train_batch_size,
+            num_workers=0,
+            collate_fn=collate_fn,
+        )
+        return dataloader
+
+    accelerator.state.deepspeed_plugin.deepspeed_config[
+        'train_micro_batch_size_per_gpu'] = args.per_device_train_batch_size
+    accelerator.state.deepspeed_plugin.deepspeed_config[
+        'gradient_accumulation_steps'] = args.gradient_accumulation_steps
+    accelerator.state.deepspeed_plugin.deepspeed_config[
+        'steps_per_print'] = args.steps_per_print
+
+    # Make one log on every process with the configuration for debugging.
+    logging.basicConfig(
+        format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
+        datefmt="%m/%d/%Y %H:%M:%S",
+        level=logging.INFO,
+    )
+    logger.info(accelerator.state, main_process_only=False)
+    if accelerator.is_local_main_process:
+        transformers.utils.logging.set_verbosity_info()
+    else:
+        transformers.utils.logging.set_verbosity_error()
+
+    # If passed along, set the training seed now.
+    if args.seed is not None:
+        set_seed(args.seed)
+
+    # Handle the repository creation
+    if accelerator.is_main_process:
+        os.makedirs(args.output_dir, exist_ok=True)
+    accelerator.wait_for_everyone()
+
+    config = AutoConfig.from_pretrained(
+        args.model_name_or_path,
+        trust_remote_code=args.trust_remote_code,
+    )
+    processor = AutoProcessor.from_pretrained(args.model_name_or_path)
+
+    model = Qwen2AudioForConditionalGeneration.from_pretrained(
+        args.model_name_or_path,
+        from_tf=bool(".ckpt" in args.model_name_or_path),
+        config=config,
+        low_cpu_mem_usage=args.low_cpu_mem_usage,
+        trust_remote_code=args.trust_remote_code,
+        # Qwen2AudioForConditionalGeneration can not support `flash_attention` but we keep it here for demonstration
+        attn_implementation="flash_attention_2" if args.flash_attention else None,
+        torch_dtype=config.torch_dtype
+    )
+
+    if args.lora:
+        logger.info("Use lora to finetune...")
+        peft_config = LoraConfig(
+            task_type=TaskType.CAUSAL_LM,
+            inference_mode=False,
+            r=8,
+            lora_alpha=32,
+            lora_dropout=0.1,
+            init_lora_weights="gaussian",
+            target_modules=["q_proj", "k_proj", "v_proj"]
+        )
+        model.enable_input_require_grads()
+        model = get_peft_model(model, peft_config)
+        model.print_trainable_parameters()
+
+    if args.gradient_checkpointing:
+        model.gradient_checkpointing_enable()
+
+    # We resize the embeddings only when necessary to avoid index errors. If you are creating a model from scratch
+    # on a small vocab and want a smaller embedding size, remove this test.
+    embedding_size = model.get_input_embeddings().weight.shape[0]
+    if len(processor.tokenizer) > embedding_size:
+        model.resize_token_embeddings(len(processor.tokenizer))
+
+    # Prepare the dataloader
+    train_dataloader = init_dataloader(processor)
+
+    # Optimizer
+    # Split weights in two groups, one with weight decay and the other not.
+    no_decay = ["bias", "layer_norm.weight"]
+    optimizer_grouped_parameters = [
+        {
+            "params": [p for n, p in model.named_parameters() if not any(nd in n for nd in no_decay) and p.requires_grad],
+            "weight_decay": args.weight_decay,
+        },
+        {
+            "params": [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay) and p.requires_grad],
+            "weight_decay": 0.0,
+        },
+    ]
+    optimizer = torch.optim.AdamW(
+        optimizer_grouped_parameters,
+        lr=args.learning_rate
+    )
+
+    # Scheduler and math around the number of training steps.
+    lr_scheduler = get_scheduler(
+        name=args.lr_scheduler_type,
+        optimizer=optimizer,
+        num_warmup_steps=args.num_warmup_steps * accelerator.num_processes,
+        num_training_steps=args.max_train_steps * accelerator.num_processes
+    )
+
+    # Prepare everything with our `accelerator`.
+    model, optimizer, lr_scheduler, train_dataloader = accelerator.prepare(
+        model, optimizer, lr_scheduler, train_dataloader
+    )
+
+    # Train!
+    total_batch_size = args.per_device_train_batch_size * \
+        accelerator.num_processes * args.gradient_accumulation_steps
+
+    logger.info("***** Running training *****")
+    logger.info(
+        f"  Instantaneous batch size per device = {args.per_device_train_batch_size}")
+    logger.info(
+        f"  Total train batch size (w. parallel, distributed & accumulation) = {total_batch_size}")
+    logger.info(
+        f"  Gradient Accumulation steps = {args.gradient_accumulation_steps}")
+    logger.info(f"  Total optimization steps = {args.max_train_steps}")
+    logger.info(f"  Num processes: {accelerator.num_processes}")
+    logger.info(f"  Process index: {accelerator.process_index}")
+
+    completed_steps = 0
+
+    for _, batch in enumerate(train_dataloader):
+        model.train()
+
+        with accelerator.accumulate(model):
+            # Move the batch to the device (should be done by the accelerator)
+            for k, v in batch.items():
+                if isinstance(v, torch.Tensor) and v.device == torch.device("cpu"):
+                    batch[k] = v.cuda()
+
+            outputs = model(**batch)
+            loss = outputs.loss
+            # We keep track of the loss at each step
+            local_loss = loss.detach().float()
+            logger.info(
+                f"Steps = {completed_steps + 1}, Local loss = {local_loss}...")
+            accelerator.backward(loss)
+            optimizer.step()
+            lr_scheduler.step()
+            optimizer.zero_grad()
+
+        # Checks if the accelerator has performed an optimization step behind the scenes
+        if accelerator.sync_gradients:
+            completed_steps += 1
+
+        if args.output_dir is not None and completed_steps % args.save_interval == 0:
+            accelerator.wait_for_everyone()
+            output_dir = os.path.join(
+                args.output_dir,
+                f"checkpoint_{completed_steps}"
+            )
+            unwrapped_model = accelerator.unwrap_model(model)
+            unwrapped_model.save_pretrained(
+                output_dir, is_main_process=accelerator.is_main_process, save_function=accelerator.save
+            )
+            if accelerator.is_main_process:
+                processor.save_pretrained(output_dir)
+
+        if completed_steps >= args.max_train_steps:
+            return
+
+
+if __name__ == "__main__":
+    # Parse arguments
+    args = parse_args()
+
+    main(args)

finetune/run.sh

+export GPUS_PER_NODE=8
+export NCCL_IB_QPS_PER_CONNECTION=8
+export WORLD_SIZE=1
+export MASTER_ADDR=localhost
+export MASTER_PORT=29500
+export RANK=0
+
+# Only test deepspeed_z1.yaml but it should be the same for other configs
+accelerate launch \
+    --config_file accelerate_configs/deepspeed_z1.yaml \
+    --main_process_ip $MASTER_ADDR \
+    --main_process_port $MASTER_PORT \
+    --machine_rank $RANK \
+    --num_machines $WORLD_SIZE \
+    --num_processes $(($WORLD_SIZE * $GPUS_PER_NODE)) \
+    run.py \
+    --model_name_or_path  Qwen/Qwen2-Audio-7B-Instruct \
+    --per_device_train_batch_size 2 \
+    --gradient_accumulation_steps 1 \
+    --learning_rate 3e-5 \
+    --max_train_steps 20000 \
+    --trust_remote_code \
+    --save_interval 5 \
+    --gradient_checkpointing \
+    --lora \
+    $@
\ No newline at end of file

model.properties

+# 模型唯一标识
+modelCode = 1092
+# 模型名称
+modelName=mplug-docowl_pytorch                    
+# 模型描述
+modelDescription=多模态OCR大模型，端侧可用
+# 应用场景
+appScenario=推理,OCR,金融,教育,政府,科研,交通,广媒
+# 框架类型
+frameType=pytorch

qwen2_audio_inference.py

+from io import BytesIO
+from urllib.request import urlopen
+import librosa
+from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor
+
+processor = AutoProcessor.from_pretrained("/home/wanglch/Qwen2-Audio/Qwen2-Audio-7B-Instruct/", trust_remote_code=True)
+model = Qwen2AudioForConditionalGeneration.from_pretrained("/home/wanglch/Qwen2-Audio/Qwen2-Audio-7B-Instruct/", trust_remote_code=True, device_map="auto")
+
+conversation = [
+    {"role": "user", "content": [
+        {"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/guess_age_gender.wav"},
+    ]},
+    {"role": "assistant", "content": "Yes, the speaker is female and in her twenties."},
+    {"role": "user", "content": [
+        {"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/translate_to_chinese.wav"},
+    ]},
+]
+text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
+audios = []
+for message in conversation:
+    if isinstance(message["content"], list):
+        for ele in message["content"]:
+            if ele["type"] == "audio":
+                audios.append(librosa.load(
+                    BytesIO(urlopen(ele['audio_url']).read()), 
+                    sr=processor.feature_extractor.sampling_rate)[0]
+                )
+
+inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
+inputs.input_ids = inputs.input_ids.to("cuda")
+
+generate_ids = model.generate(**inputs, max_length=256)
+generate_ids = generate_ids[:, inputs.input_ids.size(1):]
+
+response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+print("Qwen_Audio Output:", response)