magic-pdf 1.3.6__py3-none-any.whl → 1.3.8__py3-none-any.whl

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

@@ -3,10 +3,14 @@ lang:
     det: ch_PP-OCRv3_det_infer.pth
     rec: ch_PP-OCRv4_rec_infer.pth
     dict: ppocr_keys_v1.txt
-  ch:
+  ch_server:
     det: ch_PP-OCRv3_det_infer.pth
     rec: ch_PP-OCRv4_rec_server_infer.pth
     dict: ppocr_keys_v1.txt
+  ch:
+    det: ch_PP-OCRv3_det_infer.pth
+    rec: ch_PP-OCRv4_rec_server_doc_infer.pth
+    dict: ppocrv4_doc_dict.txt
   en:
     det: en_PP-OCRv3_det_infer.pth
     rec: en_PP-OCRv4_rec_infer.pth

{magic_pdf-1.3.6.dist-info → magic_pdf-1.3.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 1.3.6
+Version: 1.3.8
 Summary: A practical tool for converting PDF to Markdown
 License: AGPL-3.0
 Project-URL: Home, https://mineru.net/
@@ -107,6 +107,15 @@ Easier to use: Just grab MinerU Desktop. No coding, no login, just a simple inte
 </div>
 
 # Changelog
+- Released on 2025/04/23, version 1.3.8
+  - The default `ocr` model (`ch`) has been updated to `PP-OCRv4_server_rec_doc` (model update required)
+    - `PP-OCRv4_server_rec_doc` is trained on a mix of more Chinese document data and PP-OCR training data, enhancing recognition capabilities for some traditional Chinese characters, Japanese, and special characters. It supports over 15,000 recognizable characters, improving text recognition in documents while also boosting general text recognition.
+    - [Performance comparison between PP-OCRv4_server_rec_doc, PP-OCRv4_server_rec, and PP-OCRv4_mobile_rec](https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/ocr_modules/text_recognition.html#ii-supported-model-list)
+    - Verified results show that the `PP-OCRv4_server_rec_doc` model significantly improves accuracy in both single-language (`Chinese`, `English`, `Japanese`, `Traditional Chinese`) and mixed-language scenarios, with speed comparable to `PP-OCRv4_server_rec`, making it suitable for most use cases.
+    - In a small number of pure English scenarios, the `PP-OCRv4_server_rec_doc` model may encounter word concatenation issues, whereas `PP-OCRv4_server_rec` performs better in such cases. Therefore, we have retained the `PP-OCRv4_server_rec` model, which users can invoke by passing the parameter `lang='ch_server'`(python api) or `--lang ch_server`(cli).
+- 2025/04/22 1.3.7 Released
+  - Fixed the issue where the `lang` parameter was ineffective during table parsing model initialization.
+  - Fixed the significant slowdown in OCR and table parsing speed in `cpu` mode.
 - 2025/04/16 1.3.4 Released
   - Slightly improved the speed of OCR detection by removing some unused blocks.
   - Fixed page-level sorting errors caused by footnotes in certain cases.

{magic_pdf-1.3.6.dist-info → magic_pdf-1.3.8.dist-info}/RECORD

@@ -52,9 +52,9 @@ magic_pdf/libs/pdf_check.py,sha256=7GWWvDR6g_rj_fE6XJlbTq5AFVX11ngRIzT0N18F214,3
 magic_pdf/libs/pdf_image_tools.py,sha256=_au7plmKKctpPKozBumSKgP8689q4vH1mU8VMLO0IbM,2260
 magic_pdf/libs/performance_stats.py,sha256=DW-c6nUTUnWKGTONRKfpucsYZm1ake016F9K7jJwbik,2136
 magic_pdf/libs/safe_filename.py,sha256=ckwcM_eqoysTb5id8czp-tXq2G9da0-l3pshZDCHQtE,236
-magic_pdf/libs/version.py,sha256=5ZbAQtod5QalTI1C2N07edlxplzG_Q2XvGOSyOok4uA,22
+magic_pdf/libs/version.py,sha256=47xEhOdVR5Y8-pZH8aVP6Z2UhhY8jGWTQ-rJHt5fIeU,22
 magic_pdf/model/__init__.py,sha256=sa-dO2k-TLy25I2gRrzjm_cQeYfzMf-pLwBJHkIxGo0,51
-magic_pdf/model/batch_analyze.py,sha256=yKhKQuZTh9GG83p61bw2BRqKMbnsjsmX73gfuTRk8xE,11272
+magic_pdf/model/batch_analyze.py,sha256=F0WsjbQ6z9txdiUiVy6n6zhyJWJ-4moljNx8fe8HFws,10977
 magic_pdf/model/doc_analyze_by_custom_model.py,sha256=-cjn7DQi6kZCqVZ0IxbXuL2kmeGhSVLzLaezIHPFzMU,10317
 magic_pdf/model/magic_model.py,sha256=yZKWo_wRck_-YLyFGRiUHGar8sV1Y6458BFLbyBAt74,30682
 magic_pdf/model/model_list.py,sha256=aqfEJlEfbib3D3ISrxc0Coh6SbffYh8Yq2FlQN35_zA,213
@@ -109,7 +109,7 @@ magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_swin/modeling_unim
 magic_pdf/model/sub_modules/ocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/ocr_utils.py,sha256=3qxu0lAjqzZQ2Ci-C_wz_YSakyq_5-KnckA3-5bICTM,12589
-magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorch_paddle.py,sha256=FaPo02L1IJKybGYfydsohOiHstJIL8d5UKzGck2tYvk,7283
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorch_paddle.py,sha256=xbQWxgeOTNvLNFSio4Too2Yyg20uikjJlyVXuQqwq3Y,7555
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/base_ocr_v20.py,sha256=5bI7MAu65r-vn28krwdJ6pjZMkEvWjspE7EQaTsRERw,1319
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/data/__init__.py,sha256=YYu3c-W4fgEErxxDM98uQ3oWwPEh-6w75LY4zcj4VtM,199
@@ -140,8 +140,8 @@ magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/postprocess/cls_pos
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/postprocess/db_postprocess.py,sha256=EAc-cmhXtxLfFA6h5C871hIcDfXsjPDISiVCKwxh-qM,6339
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/postprocess/rec_postprocess.py,sha256=HiHNr4bhW5U1j4pYoyi8fPOaFsn8TUc4nSB6q8chfV4,26899
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/arch_config.yaml,sha256=eEzg5D5L3MHFL4H02gZnxdDiqtSCUzZDnt5pqDAmgCI,6980
-magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/models_config.yml,sha256=M0vyAENxKIaPaSdRBDhH8ik5V71vcY1STkZoq-3iqD8,1504
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/arch_config.yaml,sha256=UzG7gH1unPJWwICJWdz1VNUXmetSqrSb_iR5o59Lo9A,7508
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/models_config.yml,sha256=_AjgxSML_Tj2VkARYFIrhZzrz36PZX9koGRF-xZC2ho,1629
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/arabic_dict.txt,sha256=xbaXD14RWk0Vpc7fAHpephuszp1j-Qi3IWC4VrFKu70,407
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/chinese_cht_dict.txt,sha256=gyVR_uHy-8l1CHctgevcjboSwA3pejXHHJ3fQ92sGoM,33443
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/cyrillic_dict.txt,sha256=NpqCxsjEeXhKXXJkSLg7Hq-1_vCkEppeqjkpYl3c0TI,410
@@ -152,6 +152,7 @@ magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dic
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/korean_dict.txt,sha256=qh_ciuj3zUCg7E7bRy6wQh4RQn5sz-6ZFUQHQsGLCiA,14480
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/latin_dict.txt,sha256=jm1ONil4jDXDH35TAofWFHtUm7eiZb1nCLsoETRCniw,468
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/ppocr_keys_v1.txt,sha256=KLI2KtSrLcOHaapy_rU146nds_0qdYWgWSDmOTsdx_c,26249
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/ppocrv4_doc_dict.txt,sha256=pbw4h8Q8kB5aP5exP_rfHFdU7efMjJ9aviLodafEg3I,62346
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/ta_dict.txt,sha256=6T5pSBSv2f8ekYtvS7Qmf7TGWpNE7l10ZPkTW5DAonA,352
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/te_dict.txt,sha256=7plGpg13AZd0dOiYg2lKTKIOqjhoojM0v3lA3NAI8Pk,429
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/__init__.py,sha256=xEqR65Z8YOzOLorLjK0LCHos2zX-tCuxSrxndjU00hE,49
@@ -195,9 +196,9 @@ magic_pdf/tools/common.py,sha256=-x0RSFr7SNbdYq7DntaLYmQmaxyF-xKSf4xMpSUTzA0,126
 magic_pdf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/utils/annotations.py,sha256=82ou3uELNbQWa9hOFFkVt0gsIskAKf5msCv5J2IJ5V0,211
 magic_pdf/utils/office_to_pdf.py,sha256=bFRYe6v3-pfx5R8-bV8cmf12jPnOrYZsleKoECTXzbM,3958
-magic_pdf-1.3.6.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
-magic_pdf-1.3.6.dist-info/METADATA,sha256=WciKDOUh2xH6OdTqDPJlMlLrUhaHBseO5dycx0_7RLo,45798
-magic_pdf-1.3.6.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-magic_pdf-1.3.6.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
-magic_pdf-1.3.6.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-1.3.6.dist-info/RECORD,,
+magic_pdf-1.3.8.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+magic_pdf-1.3.8.dist-info/METADATA,sha256=8DvNpL0env37CB35wE7uErGK_mxx3LVSC6Qgr1kttEM,47408
+magic_pdf-1.3.8.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+magic_pdf-1.3.8.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-1.3.8.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-1.3.8.dist-info/RECORD,,