refactor: update OCR model configurations to use v5 and enhance language handling

mineru/model/ocr/paddleocr2pytorch/pytorch_paddle.py

@@ -57,7 +57,7 @@ class PytorchPaddleOCR(TextSystem):
         self.lang = kwargs.get('lang', 'ch')
 
         device = get_device()
-        if device == 'cpu' and self.lang in ['ch', 'ch_server']:
+        if device == 'cpu' and self.lang in ['ch', 'ch_server', 'japan', 'chinese_cht']:
             logger.warning("The current device in use is CPU. To ensure the speed of parsing, the language is automatically switched to ch_lite.")
             self.lang = 'ch_lite'
 

mineru/model/ocr/paddleocr2pytorch/pytorchocr/utils/resources/arch_config.yaml

@@ -120,6 +120,22 @@ ch_PP-OCRv5_det_infer:
     name: DBHead
     k: 50
 
+ch_PP-OCRv5_det_server_infer:
+    model_type: det
+    algorithm: DB
+    Transform: null
+    Backbone:
+        name: PPHGNetV2_B4
+        det: True
+    Neck:
+        name: LKPAN
+        out_channels: 256
+        intracl: True
+    Head:
+        name: PFHeadLocal
+        k: 50
+        mode: "large"
+
 ch_PP-OCRv4_det_server_infer:
   model_type: det
   algorithm: DB

mineru/model/ocr/paddleocr2pytorch/pytorchocr/utils/resources/models_config.yml

 lang:
   ch_lite:
-    det: ch_PP-OCRv3_det_infer.pth
+    det: ch_PP-OCRv5_det_infer.pth
     rec: ch_PP-OCRv5_rec_infer.pth
     dict: ppocrv5_dict.txt
   ch_lite_v4:
-    det: ch_PP-OCRv3_det_infer.pth
+    det: ch_PP-OCRv5_det_infer.pth
     rec: ch_PP-OCRv4_rec_infer.pth
     dict: ppocr_keys_v1.txt
   ch_server:
-    det: ch_PP-OCRv3_det_infer.pth
+    det: ch_PP-OCRv5_det_infer.pth
     rec: ch_PP-OCRv5_rec_server_infer.pth
     dict: ppocrv5_dict.txt
   ch_server_v4:
-    det: ch_PP-OCRv3_det_infer.pth
+    det: ch_PP-OCRv5_det_infer.pth
     rec: ch_PP-OCRv4_rec_server_infer.pth
     dict: ppocr_keys_v1.txt
   ch:
-    det: ch_PP-OCRv3_det_infer.pth
+    det: ch_PP-OCRv5_det_infer.pth
     rec: ch_PP-OCRv4_rec_server_doc_infer.pth
     dict: ppocrv4_doc_dict.txt
   en:
@@ -28,12 +28,12 @@ lang:
     rec: korean_PP-OCRv3_rec_infer.pth
     dict: korean_dict.txt
   japan:
-    det: Multilingual_PP-OCRv3_det_infer.pth
-    rec: japan_PP-OCRv3_rec_infer.pth
+    det: ch_PP-OCRv5_det_infer.pth
+    rec: ch_PP-OCRv5_rec_server_infer.pth
     dict: japan_dict.txt
   chinese_cht:
-    det: Multilingual_PP-OCRv3_det_infer.pth
-    rec: chinese_cht_PP-OCRv3_rec_infer.pth
+    det: ch_PP-OCRv5_det_infer.pth
+    rec: ch_PP-OCRv5_rec_server_infer.pth
     dict: chinese_cht_dict.txt
   ta:
     det: Multilingual_PP-OCRv3_det_infer.pth