Merge pull request #2501 from myhloli/dev

feat(ocr): add PP-OCRv5 models and update configurations

magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/arch_config.yaml

@@ -104,6 +104,22 @@ ch_PP-OCRv4_det_infer:
     name: DBHead
     k: 50
 
+ch_PP-OCRv5_det_infer:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.75
+    det: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
 ch_PP-OCRv4_det_server_infer:
   model_type: det
   algorithm: DB
@@ -196,6 +212,32 @@ ch_PP-OCRv4_rec_server_doc_infer:
           nrtr_dim: 384
           max_text_length: 25
 
+ch_PP-OCRv5_rec_infer:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.95
+  Head:
+    name: MultiHead
+    out_channels_list:
+      CTCLabelDecode: 18385
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [ 1, 3 ]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: 25
+
 chinese_cht_PP-OCRv3_rec_infer:
   model_type: rec
   algorithm: SVTR

magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/models_config.yml

 lang:
-  ch_lite:
+  ch_lite_v4:
     det: ch_PP-OCRv3_det_infer.pth
     rec: ch_PP-OCRv4_rec_infer.pth
     dict: ppocr_keys_v1.txt
+  ch_lite:
+    det: ch_PP-OCRv5_det_infer.pth
+    rec: ch_PP-OCRv5_rec_infer.pth
+    dict: ppocrv5_dict.txt
   ch_server:
     det: ch_PP-OCRv3_det_infer.pth
     rec: ch_PP-OCRv4_rec_server_infer.pth