magic-pdf 1.3.11__py3-none-any.whl → 1.3.12__py3-none-any.whl

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

@@ -1,9 +1,17 @@
 lang:
   ch_lite:
+    det: ch_PP-OCRv3_det_infer.pth
+    rec: ch_PP-OCRv5_rec_infer.pth
+    dict: ppocrv5_dict.txt
+  ch_lite_v4:
     det: ch_PP-OCRv3_det_infer.pth
     rec: ch_PP-OCRv4_rec_infer.pth
     dict: ppocr_keys_v1.txt
   ch_server:
+    det: ch_PP-OCRv3_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
     rec: ch_PP-OCRv4_rec_server_infer.pth
     dict: ppocr_keys_v1.txt

{magic_pdf-1.3.11.dist-info → magic_pdf-1.3.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 1.3.11
+Version: 1.3.12
 Summary: A practical tool for converting PDF to Markdown
 License: AGPL-3.0
 Project-URL: Home, https://mineru.net/
@@ -107,6 +107,20 @@ Easier to use: Just grab MinerU Desktop. No coding, no login, just a simple inte
 </div>
 
 # Changelog
+- 2025/05/24 1.3.12 Released
+  - Added support for ppocrv5 model, updated `ch_server` model to `PP-OCRv5_rec_server` and `ch_lite` model to `PP-OCRv5_rec_mobile` (model update required)
+    - In testing, we found that ppocrv5(server) shows some improvement for handwritten documents, but slightly lower accuracy than v4_server_doc for other document types. Therefore, the default ch model remains unchanged as `PP-OCRv4_server_rec_doc`.
+    - Since ppocrv5 enhances recognition capabilities for handwritten text and special characters, you can manually select ppocrv5 models for Japanese, traditional Chinese mixed scenarios and handwritten document scenarios
+    - You can select the appropriate model through the lang parameter `lang='ch_server'` (python api) or `--lang ch_server` (command line):
+      - `ch`: `PP-OCRv4_rec_server_doc` (default) (Chinese, English, Japanese, Traditional Chinese mixed/15k dictionary)
+      - `ch_server`: `PP-OCRv5_rec_server` (Chinese, English, Japanese, Traditional Chinese mixed + handwriting/18k dictionary)
+      - `ch_lite`: `PP-OCRv5_rec_mobile` (Chinese, English, Japanese, Traditional Chinese mixed + handwriting/18k dictionary)
+      - `ch_server_v4`: `PP-OCRv4_rec_server` (Chinese, English mixed/6k dictionary)
+      - `ch_lite_v4`: `PP-OCRv4_rec_mobile` (Chinese, English mixed/6k dictionary)
+  - Added support for handwritten documents by optimizing layout recognition of handwritten text areas
+    - This feature is supported by default, no additional configuration needed
+    - You can refer to the instructions above to manually select ppocrv5 model for better handwritten document parsing
+  - The demos on `huggingface` and `modelscope` have been updated to support handwriting recognition and ppocrv5 models, which you can experience online
 - 2025/04/29 1.3.10 Released
   - Support for custom formula delimiters can be achieved by modifying the `latex-delimiter-config` item in the `magic-pdf.json` file under the user directory.
 - 2025/04/27 1.3.9 Released  

{magic_pdf-1.3.11.dist-info → magic_pdf-1.3.12.dist-info}/RECORD

@@ -14,7 +14,7 @@ magic_pdf/data/batch_build_dataset.py,sha256=KQoWFJDqCwRQug8-fTuciSwff58AYRjCNP6
 magic_pdf/data/dataset.py,sha256=2v-a7kA6dRUDQpjlAVE5We1tMATR-MYKzQCcBhNci5g,12258
 magic_pdf/data/read_api.py,sha256=qcG0T4c4ME5CkSRDjX2Wa2JQ_HW4GqzXAixI3_DZG_U,5234
 magic_pdf/data/schemas.py,sha256=oIUTBzK8Wq8Wuy8A_uilWAbVhucRvOs9_f3lSKYgcmQ,664
-magic_pdf/data/utils.py,sha256=dNWIJECPXaakKocI4z5Tq6vhDDSnR-bVWQV7DO2w_A8,5335
+magic_pdf/data/utils.py,sha256=SA91UzbB6kS_24YVRtZ6HRpKPeCc6Ea4EaQNUuwQio8,5339
 magic_pdf/data/data_reader_writer/__init__.py,sha256=QtevUaeSivv9dQKi3Tomfn4Z0E4To0cB8qXTnglxaHc,705
 magic_pdf/data/data_reader_writer/base.py,sha256=nqmAcdHOXMOJO6RAT3ILligDFaw8Op0STyCw5yOzAbI,1706
 magic_pdf/data/data_reader_writer/filebase.py,sha256=VbNAxLyo0Io0j7iprJERt_TqxzHAtA7cUyPIaJstToU,2146
@@ -25,7 +25,7 @@ magic_pdf/data/io/base.py,sha256=SqNQqe30ZvoVvg7GVv-hLMCjN6yBgDyQQWeLgGsTfhQ,111
 magic_pdf/data/io/http.py,sha256=XlKB0DNf4a_uUnfgcclvaaOtmE7lmddx0DnK8A-emAM,958
 magic_pdf/data/io/s3.py,sha256=hyA7sbNriQy64xd_uyJ7acN_oneQ1Pdmoc7_xcvkue8,3606
 magic_pdf/dict2md/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/dict2md/ocr_mkcontent.py,sha256=jRGoSNeR3XBgzGhKdQ25CmsdW0pi7NA-5NY3TB2pja0,14421
+magic_pdf/dict2md/ocr_mkcontent.py,sha256=cb9yd-PBEnc-rpyhvcNlmFJyTlhUNDnwY4LMMDz8mSM,15369
 magic_pdf/filter/__init__.py,sha256=_7lSez_myu4b6cdzPpQ-NfREuqeBSq_QdyBPKVLyq2U,1505
 magic_pdf/filter/pdf_classify_by_type.py,sha256=YNYXamxYgEiSujwilCNHOtrwpgJGDiQ597qJfardDVc,42354
 magic_pdf/filter/pdf_meta_scan.py,sha256=eOuM0-JgaXvHolSgepGoNDJDmv_uITWLQpH_0MfnVQw,17478
@@ -52,17 +52,17 @@ 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=cYqar-M7VsRkfFRByjCNAq9dYm1GavgcND7ugDzle7Q,23
+magic_pdf/libs/version.py,sha256=2Rgd7p7gALBiXufv4uSeaC9anR_muEfi4m5NMAgfMHI,23
 magic_pdf/model/__init__.py,sha256=sa-dO2k-TLy25I2gRrzjm_cQeYfzMf-pLwBJHkIxGo0,51
-magic_pdf/model/batch_analyze.py,sha256=F0WsjbQ6z9txdiUiVy6n6zhyJWJ-4moljNx8fe8HFws,10977
-magic_pdf/model/doc_analyze_by_custom_model.py,sha256=R-d3_ZLZtlAztA23yaDvC0YC2-heXxrBBEyGlX7or7c,10547
+magic_pdf/model/batch_analyze.py,sha256=Lt2wcnxjfwEtdzZ5ALkoHhchxFQXgLykdngBkkgDzoE,11666
+magic_pdf/model/doc_analyze_by_custom_model.py,sha256=Vpa3C78ZKi2o6ViXjNiDfEzaHM6l5dYDDrexJYFmWKM,10547
 magic_pdf/model/magic_model.py,sha256=yZKWo_wRck_-YLyFGRiUHGar8sV1Y6458BFLbyBAt74,30682
 magic_pdf/model/model_list.py,sha256=aqfEJlEfbib3D3ISrxc0Coh6SbffYh8Yq2FlQN35_zA,213
 magic_pdf/model/pdf_extract_kit.py,sha256=C3sKqRkoD20Ldmo-cqGn1zRldEL-l5NYqcFvd05_fGU,10845
 magic_pdf/model/pp_structure_v2.py,sha256=NcqFWL4nUtjl82MFak8HX_8V3i4Aw_fK4dATrIp5uGs,3840
 magic_pdf/model/sub_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/model/sub_modules/model_init.py,sha256=e2t95kxiuU47luOHByDokbQ2uob6oQhEA4b6UGVfMjY,8303
-magic_pdf/model/sub_modules/model_utils.py,sha256=Md5yOki9uqW31sWIi7AKRwAJNKnCJBVSfQx6LXRKngs,12166
+magic_pdf/model/sub_modules/model_utils.py,sha256=uZnI93ZNnTBPb8ajCDGvPlJY3m0O54NKO5e8ySfIbCc,12219
 magic_pdf/model/sub_modules/language_detection/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 magic_pdf/model/sub_modules/language_detection/utils.py,sha256=Q__v6DdNJztt8GhVSuSB0txahVq-aj8RLhWn2VScx4w,3047
 magic_pdf/model/sub_modules/language_detection/yolov11/YOLOv11.py,sha256=7T8eFl8zlZe6F0j0jSB3jrwOapDft320JQ1fuWxpvAY,5230
@@ -119,12 +119,13 @@ magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/__init__.p
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/common.py,sha256=3r2jTvPYQS4IgTvIqR4l6bBVwR7jn-87rSmpv3tlqxI,2294
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/architectures/__init__.py,sha256=DCA9FS4mE5oCHDlBhUrkYLdxFeQIbhPj4P8oJ_gRZD8,832
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/architectures/base_model.py,sha256=RhV2Dm-os08kCFylT57zRu72Hq_RJdFy3xQe1MPaCuU,3588
-magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/__init__.py,sha256=TOLvLNeJhnAOus0D5jAq2TM67vLrtbzYlThTOhc-idc,1960
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/__init__.py,sha256=Y2U-bQ7xVSh6MMTGzc7rb0kbMq_QniZiP7_CYIvONXk,2035
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/det_mobilenet_v3.py,sha256=r0gWnA1Xmt0Zw4FQLx7kf-WWwZd_26PfNzhM05drcuE,8334
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_hgnet.py,sha256=UsIbzqN_koyGoSh1TA9r27SggpHbeKS3HmmS-A2Aw04,8341
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_lcnetv3.py,sha256=3PNQG9B1cHe1hAg0NhcFR8p87rZnmH0jTBcfid-ZnKQ,15995
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_mobilenet_v3.py,sha256=mJmE6xGpjHZH2Vaw16LlIlqRFFm9R9yRsSJEa3Yn3nw,4822
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_mv1_enhance.py,sha256=K4p9KFYNmltV3y3QsxHIASNxoqlGtxgAoCxeFofyCmw,6726
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_pphgnetv2.py,sha256=RIyHwb_jzDmwn6zGTD4LoK4n9HYxBvvb-QlUMnDk3fk,27525
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_svtrnet.py,sha256=AIaUZ3IWBkRz2pWmanBjS0QdJcYnimMSV4MWofNpQcg,20222
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/heads/__init__.py,sha256=7vl3hyn6Ug_DNtqdfUL1Hz9scA_ptch2FCDzNddpQgU,1282
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/heads/cls_head.py,sha256=puIy5GlUtAKer6eS4HWKu07PzRd-HlDAqIz5WqjBHaA,596
@@ -134,14 +135,14 @@ magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/heads/rec_
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/__init__.py,sha256=634L1y-QWv5P8opNiSmKvQEx3Uskc20RG8DYiCdbl8U,1030
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/db_fpn.py,sha256=TLF2pSyvRC0oPzL0eVyNlg3W6Zvfr4J8fD1nziVB7uI,14146
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/intracl.py,sha256=w2QdwdI9BpiW92VS4mqL31sVERIbY53TfbD5Q6okiaY,3410
-magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/rnn.py,sha256=olZwnKQexVlMx0gJi0FVYAm38TxNn5BM6F-OrdHKEgk,7019
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/rnn.py,sha256=F0Iw-3IHuh4jcWy2b1Tyb8IRinDkiAvTSdtnWDfWzUc,7488
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/postprocess/__init__.py,sha256=iC1Ol6CTxRWZBUyQ_5IVMR6kIurv9WJPOWWo7NAuZBA,1183
 magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/postprocess/cls_postprocess.py,sha256=1VVWXT_b1vhGb7PGvqyfUQ3Ip7LupH62vPva98GtjTA,685
 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=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/arch_config.yaml,sha256=-KTBQ8MEI_mCTAHVuMoNmsXV7DmkkYcjriLwDwrPi3Y,8817
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/models_config.yml,sha256=RoWRKzU9nvwYnVAHae9HcDR-t0OyrS6NLZ2hgZcolrY,1860
 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
@@ -153,6 +154,7 @@ magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dic
 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/ppocrv5_dict.txt,sha256=0Zeen3lMRkwNLgtwp_4U3ZeOncZEwOcfFBWM34NCrxs,74012
 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
@@ -196,9 +198,9 @@ 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-1.3.11.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
-magic_pdf-1.3.11.dist-info/METADATA,sha256=MFffMcv9-ZlVG8jBKDtTPofJC_F-x_OPU4aLwxd-aUs,47765
-magic_pdf-1.3.11.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-magic_pdf-1.3.11.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
-magic_pdf-1.3.11.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-1.3.11.dist-info/RECORD,,
+magic_pdf-1.3.12.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+magic_pdf-1.3.12.dist-info/METADATA,sha256=9UO2LqbOUz-SEObMHTrJaatZElHw4jrD_c4aQFC6q9I,49562
+magic_pdf-1.3.12.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+magic_pdf-1.3.12.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-1.3.12.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-1.3.12.dist-info/RECORD,,