@@ -5,30 +5,9 @@ description = "Add your description here"
55readme = " README.md"
66requires-python = " >=3.10"
77dependencies = [
8- " beautifulsoup4>=4.14.3" ,
9- " datasketch>=1.8.0" ,
10- " email-validator>=2.3.0" ,
11- " emoji>=2.15.0" ,
12- " jieba>=0.42.1" ,
13- " loguru>=0.7.3" ,
14- " mineru>=2.6.5" ,
15- " numpy>=2.2.6" ,
16- " python-multipart>=0.0.20" ,
17- " opencv-contrib-python-headless>=4.12.0.88" ,
18- " opencv-python-headless>=4.12.0.88" ,
19- " paddleocr==3.4.0" ,
20- " paddlepaddle==3.2.2" ,
21- " pandas>=2.2.3,<3.0.0" ,
22- " presidio-analyzer==2.2.25" ,
23- " presidio-anonymizer==2.2.25" ,
24- " pycryptodome>=3.23.0" ,
25- " python-docx>=1.2.0" ,
26- " pytz>=2025.2" ,
27- " six>=1.17.0" ,
28- " spacy>=3.7.0" ,
29- " sqlalchemy>=2.0.44" ,
30- " xmltodict>=1.0.2" ,
31- " zhconv>=1.4.3" ,
8+ " absl-py==2.4.0" ,
9+ " accelerate==1.10.1" ,
10+ " aiofiles==25.1.0" ,
3211 " aiohappyeyeballs==2.6.1" ,
3312 " aiohttp==3.13.3" ,
3413 " aiosignal==1.4.0" ,
@@ -38,89 +17,220 @@ dependencies = [
3817 " anyio==4.12.1" ,
3918 " async-timeout==5.0.1" ,
4019 " attrs==26.1.0" ,
20+ " audioread==3.1.0" ,
4121 " av==15.1.0" ,
4222 " bce-python-sdk==0.9.60" ,
23+ " beautifulsoup4==4.14.3" ,
24+ " blinker==1.9.0" ,
25+ " blis==1.3.3" ,
26+ " boto3==1.42.97" ,
27+ " botocore==1.42.97" ,
28+ " catalogue==2.0.10" ,
4329 " certifi==2026.2.25" ,
30+ " cffi==2.0.0" ,
4431 " chardet==5.2.0" ,
4532 " charset-normalizer==3.4.4" ,
46- " click==8.1.8" ,
33+ " click==8.3.1" ,
34+ " cloudpathlib==0.23.0" ,
35+ " cobble==0.1.4" ,
4736 " coloredlogs==15.0.1" ,
4837 " colorlog==6.10.1" ,
38+ " confection==1.3.3" ,
4939 " contourpy==1.3.0" ,
40+ " cryptography==47.0.0" ,
5041 " ctranslate2==4.7.1" ,
5142 " cycler==0.12.1" ,
43+ " cymem==2.0.13" ,
5244 " datasets==4.5.0" ,
45+ " datasketch==1.10.0" ,
46+ " decorator==5.2.1" ,
47+ " deepspeed==0.13.2" ,
5348 " dill==0.4.0" ,
49+ " distro==1.9.0" ,
50+ " dnspython==2.8.0" ,
51+ " einops==0.8.2" ,
52+ " email-validator==2.3.0" ,
53+ " emoji==2.15.0" ,
54+ " et_xmlfile==2.0.0" ,
5455 " exceptiongroup==1.3.1" ,
56+ " faiss-cpu==1.13.2" ,
57+ " fast-langdetect==0.2.5" ,
58+ " fastapi==0.136.1" ,
5559 " faster-whisper==1.2.1" ,
60+ " fasttext-predict==0.9.2.4" ,
5661 " filelock==3.19.1" ,
62+ " Flask==3.1.3" ,
5763 " flatbuffers==25.12.19" ,
5864 " fonttools==4.60.2" ,
5965 " frozenlist==1.8.0" ,
6066 " fsspec==2025.10.0" ,
6167 " future==1.0.0" ,
68+ " greenlet==3.5.0" ,
69+ " grpcio==1.80.0" ,
6270 " h11==0.16.0" ,
6371 " hf-xet==1.4.2" ,
72+ " hjson==3.1.0" ,
6473 " httpcore==1.0.9" ,
6574 " httpx==0.28.1" ,
66- " huggingface-hub==1.7.2" ,
75+ " httpx-retries==0.5.0" ,
76+ " huggingface_hub==0.36.2" ,
6777 " humanfriendly==10.0" ,
78+ " HyperPyYAML==1.2.2" ,
6879 " idna==3.11" ,
80+ " ImageIO==2.37.3" ,
6981 " imagesize==1.5.0" ,
82+ " importlib_metadata==8.7.1" ,
7083 " importlib_resources==6.5.2" ,
84+ " iopath==0.1.10" ,
85+ " itsdangerous==2.2.0" ,
86+ " jieba==0.42.1" ,
7187 " Jinja2==3.1.6" ,
88+ " jiter==0.14.0" ,
89+ " jmespath==1.1.0" ,
90+ " joblib==1.3.2" ,
91+ " json_repair==0.59.5" ,
7292 " kiwisolver==1.4.7" ,
93+ " langid==1.1.6" ,
7394 " lap==0.5.13" ,
74- " llvmlite==0.43.0" ,
95+ " layoutparser==0.3.4" ,
96+ " lazy-loader==0.5" ,
97+ " librosa==0.10.2.post1" ,
98+ " llvmlite==0.44.0" ,
99+ " loguru==0.7.3" ,
100+ " lxml==6.1.0" ,
101+ " magika==1.0.2" ,
102+ " mammoth==1.12.0" ,
103+ " Markdown==3.10.2" ,
75104 " markdown-it-py==3.0.0" ,
76105 " MarkupSafe==3.0.3" ,
77106 " matplotlib==3.9.4" ,
78107 " mdurl==0.1.2" ,
108+ " mineru==3.1.6" ,
109+ " mineru_vl_utils==0.2.6" ,
79110 " modelscope==1.34.0" ,
80111 " more-itertools==10.8.0" ,
81112 " mpmath==1.3.0" ,
113+ " msgpack==1.1.2" ,
82114 " multidict==6.7.1" ,
83115 " multiprocess==0.70.18" ,
116+ " murmurhash==1.0.15" ,
84117 " networkx==3.2.1" ,
85- " numba==0.60.0" ,
118+ " ninja==1.13.0" ,
119+ " numba==0.61.2" ,
120+ " numpy==2.2.6" ,
121+ " nvidia-ml-py==13.595.45" ,
86122 " onnxruntime==1.19.2" ,
123+ " openai==2.33.0" ,
87124 " openai-whisper==20250625" ,
88125 " opencc-python-reimplemented==0.1.7" ,
126+ " opencv-contrib-python==4.10.0.84" ,
127+ " opencv-contrib-python-headless==4.13.0.92" ,
128+ " opencv-python==4.13.0.92" ,
129+ " opencv-python-headless==4.13.0.92" ,
130+ " openpyxl==3.1.5" ,
131+ " openslide-python==1.4.3" ,
89132 " opt-einsum==3.3.0" ,
90133 " packaging==26.0" ,
91- " paddlex==3.4.2" ,
134+ " paddleocr==3.3.0" ,
135+ " paddlepaddle==3.2.2" ,
136+ " paddlex==3.3.6" ,
137+ " pandas==2.3.3" ,
138+ " pdf2image==1.17.0" ,
139+ " pdfminer.six==20251230" ,
140+ " pdfplumber==0.11.9" ,
141+ " pdftext==0.6.3" ,
142+ " phonenumbers==9.0.29" ,
92143 " pillow==11.3.0" ,
144+ " platformdirs==4.9.6" ,
93145 " polars==1.36.1" ,
94146 " polars-runtime-32==1.36.1" ,
147+ " pooch==1.9.0" ,
148+ " portalocker==3.2.0" ,
149+ " preshed==3.0.13" ,
150+ " presidio-analyzer==2.2.25" ,
151+ " presidio-anonymizer==2.2.25" ,
95152 " prettytable==3.16.0" ,
96153 " propcache==0.4.1" ,
97154 " protobuf==6.33.5" ,
98155 " psutil==7.2.2" ,
156+ " ptflops==0.7" ,
99157 " py-cpuinfo==9.0.0" ,
158+ " pyahocorasick==2.3.1" ,
100159 " pyarrow==21.0.0" ,
101160 " pyclipper==1.3.0.post6" ,
161+ " pycorrector==1.1.3" ,
162+ " pycparser==3.0" ,
163+ " pycryptodome==3.23.0" ,
102164 " pydantic==2.12.5" ,
165+ " pydantic-settings==2.14.0" ,
103166 " pydantic_core==2.41.5" ,
167+ " pydub==0.25.1" ,
104168 " Pygments==2.19.2" ,
169+ " pylatexenc==2.10" ,
170+ " pynvml==13.0.1" ,
105171 " pyparsing==3.3.2" ,
106- " pypdfium2==5.5.0" ,
172+ " pypdf==6.10.2" ,
173+ " pypdfium2==4.30.0" ,
174+ " pypinyin==0.55.0" ,
175+ " pypptx-with-oxml==1.0.3" ,
176+ " pytesseract==0.3.13" ,
107177 " python-bidi==0.6.7" ,
108178 " python-dateutil==2.9.0.post0" ,
179+ " python-docx==1.2.0" ,
180+ " python-dotenv==1.2.2" ,
181+ " python-multipart==0.0.27" ,
182+ " pytz==2026.1.post1" ,
109183 " PyYAML==6.0.2" ,
184+ " qwen-vl-utils==0.0.14" ,
185+ " rapidocr-onnxruntime==1.4.4" ,
110186 " regex==2026.1.15" ,
187+ " reportlab==4.4.10" ,
111188 " requests==2.32.5" ,
189+ " requests-file==3.0.1" ,
112190 " rich==14.3.3" ,
191+ " robust-downloader==0.0.2" ,
113192 " ruamel.yaml==0.19.1" ,
193+ " s3transfer==0.16.1" ,
114194 " safetensors==0.7.0" ,
195+ " scikit-image==0.26.0" ,
196+ " scikit-learn==1.8.0" ,
115197 " scipy==1.13.1" ,
198+ " sentence-transformers==5.4.1" ,
199+ " sentencepiece==0.2.1" ,
116200 " shapely==2.0.7" ,
117201 " shellingham==1.5.4" ,
202+ " six==1.17.0" ,
203+ " smart_open==7.6.0" ,
204+ " sniffio==1.3.1" ,
205+ " soundfile==0.12.1" ,
206+ " soupsieve==2.8.3" ,
207+ " soxr==1.0.0" ,
208+ " spacy==3.8.14" ,
209+ " spacy-legacy==3.0.12" ,
210+ " spacy-loggers==1.0.5" ,
211+ " speechbrain==1.0.3" ,
212+ " SQLAlchemy==2.0.49" ,
213+ " srsly==2.5.3" ,
214+ " starlette==1.0.0" ,
118215 " sympy==1.14.0" ,
216+ " tensorboard==2.16.2" ,
217+ " tensorboard-data-server==0.7.2" ,
218+ " tensorboardX==2.6.2.2" ,
219+ " TextGrid==1.6.1" ,
220+ " thinc==8.3.13" ,
221+ " threadpoolctl==3.6.0" ,
222+ " tifffile==2026.3.3" ,
119223 " tiktoken==0.12.0" ,
224+ " timm==1.0.26" ,
225+ " tldextract==5.3.1" ,
120226 " tokenizers==0.22.2" ,
121227 " torch==2.8.0" ,
228+ " torch_npu==2.8.0" ,
229+ " torchaudio==2.8.0" ,
230+ " torchlibrosa==0.0.4" ,
122231 " torchvision==0.23.0" ,
123232 " tqdm==4.67.3" ,
233+ " transformers==4.57.6" ,
124234 " typer==0.23.2" ,
125235 " typing-inspection==0.4.2" ,
126236 " typing_extensions==4.15.0" ,
@@ -129,53 +239,16 @@ dependencies = [
129239 " ultralytics==8.4.19" ,
130240 " ultralytics-thop==2.0.18" ,
131241 " urllib3==2.6.3" ,
242+ " uvicorn==0.46.0" ,
243+ " wasabi==1.1.3" ,
132244 " wcwidth==0.6.0" ,
245+ " weasel==1.0.0" ,
246+ " Werkzeug==3.1.8" ,
247+ " wrapt==2.1.2" ,
248+ " xlsxwriter==3.2.9" ,
249+ " xmltodict==1.0.4" ,
133250 " xxhash==3.6.0" ,
134251 " yarl==1.22.0" ,
252+ " zhconv==1.4.3" ,
135253 " zipp==3.23.0" ,
136- " accelerate==1.12.0" ,
137- " blinker==1.9.0" ,
138- " Flask==3.1.3" ,
139- " itsdangerous==2.2.0" ,
140- " qwen-vl-utils==0.0.14" ,
141- " torch-npu==2.9.0" ,
142- " transformers==5.2.0" ,
143- " typer-slim==0.24.0" ,
144- " Werkzeug==3.1.6" ,
145- " layoutparser==0.3.4" ,
146- " pdf2image==1.17.0" ,
147- " pytesseract==0.3.13" ,
148- " timm==1.0.24" ,
149- " unstructured==0.11.0" ,
150- " unstructured-inference==0.7.15" ,
151- " vllm==0.13.0" ,
152- " vllm-ascend==0.13.0" ,
153- " openslide-python==1.4.2" ,
154- " joblib==1.5.3" ,
155- " scikit-learn==1.6.1" ,
156- " openpyxl" ,
157- " albumentations" ,
158- " SimpleITK" ,
159- " scikit-image" ,
160- " natsort" ,
161- " torchinfo" ,
162- " sentence-transformers==5.1.2" ,
163- " faiss-cpu==1.13.0" ,
164- " pycorrector==1.1.3" ,
165- " deepspeed==0.13.2" ,
166- " einops==0.7.0" ,
167- " hyperpyyaml==1.2.2" ,
168- " langid==1.1.6" ,
169- " librosa==0.10.2.post1" ,
170- " ptflops==0.7" ,
171- " pydub==0.25.1" ,
172- " sentencepiece==0.1.99" ,
173- " soundfile==0.12.1" ,
174- " speechbrain==1.0.3" ,
175- " tensorboard==2.16.2" ,
176- " tensorboardX==2.6.2.2" ,
177- " textgrid==1.6.1" ,
178- " torchaudio==2.2.0" ,
179- " torchlibrosa==0.0.4" ,
180- " imageio-ffmpeg>=0.6.0" ,
181254]
0 commit comments