magic-pdf 1.3.7__py3-none-any.whl → 1.3.8__py3-none-any.whl

magic_pdf/libs/version.py

@@ -1 +1 @@
-__version__ = "1.3.7"
+__version__ = "1.3.8"

magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorch_paddle.py

@@ -55,7 +55,8 @@ class PytorchPaddleOCR(TextSystem):
         self.lang = kwargs.get('lang', 'ch')
 
         device = get_device()
-        if device == 'cpu' and self.lang == 'ch':
+        if device == 'cpu' and self.lang in ['ch', 'ch_server']:
+            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'
 
         if self.lang in latin_lang:
@@ -79,7 +80,7 @@ class PytorchPaddleOCR(TextSystem):
         kwargs['rec_char_dict_path'] = os.path.join(root_dir, 'pytorchocr', 'utils', 'resources', 'dict', dict_file)
         # kwargs['rec_batch_num'] = 8
 
-        kwargs['device'] = get_device()
+        kwargs['device'] = device
 
         default_args = vars(args)
         default_args.update(kwargs)

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

@@ -171,6 +171,31 @@ ch_PP-OCRv4_rec_server_infer:
           nrtr_dim: 384
           max_text_length: 25
 
+ch_PP-OCRv4_rec_server_doc_infer:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: PPHGNet_small
+  Head:
+    name: MultiHead
+    out_channels_list:
+      CTCLabelDecode: 15631
+    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