写好了v3版本的训练代码(v3版本加入了自然场景训练增强)

requirements.txt

@@ -1,75 +1,13 @@
-absl-py==2.0.0
-accelerate==0.26.0
-aiohttp==3.9.1
-aiosignal==1.3.1
-async-timeout==4.0.3
-attrs==23.2.0
-cachetools==5.3.2
-certifi==2023.11.17
-charset-normalizer==3.3.2
-datasets==2.16.1
-dill==0.3.7
-filelock==3.13.1
-frozenlist==1.4.1
-fsspec==2023.10.0
-google-auth==2.26.2
-google-auth-oauthlib==1.2.0
-grpcio==1.60.0
-huggingface-hub==0.20.2
-idna==3.6
-Jinja2==3.1.2
-Markdown==3.5.2
-MarkupSafe==2.1.3
-mpmath==1.3.0
-multidict==6.0.4
-multiprocess==0.70.15
-networkx==3.2.1
-numpy==1.26.3
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==8.9.2.26
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-nccl-cu12==2.18.1
-nvidia-nvjitlink-cu12==12.3.101
-nvidia-nvtx-cu12==12.1.105
-oauthlib==3.2.2
-packaging==23.2
-pandas==2.1.4
-pillow==10.2.0
-protobuf==4.23.4
-psutil==5.9.7
-pyarrow==14.0.2
-pyarrow-hotfix==0.6
-pyasn1==0.5.1
-pyasn1-modules==0.3.0
-python-dateutil==2.8.2
-pytz==2023.3.post1
-PyYAML==6.0.1
-regex==2023.12.25
-requests==2.31.0
-requests-oauthlib==1.3.1
-rsa==4.9
-safetensors==0.4.1
-six==1.16.0
-sympy==1.12
-tensorboard==2.15.1
-tensorboard-data-server==0.7.2
-tensorboardX==2.6.2.2
-tokenizers==0.15.0
-torch==2.1.2
-torchaudio==2.1.2
-torchvision==0.16.2
-tqdm==4.66.1
-transformers==4.36.2
-triton==2.1.0
-typing_extensions==4.9.0
-tzdata==2023.4
-urllib3==2.1.0
-Werkzeug==3.0.1
-xxhash==3.4.1
-yarl==1.9.4
+transformers
+datasets
+evaluate
+streamlit
+opencv-python
+ray[serve]
+accelerate
+tensorboardX
+nltk
+python-multipart
+
+pdf2image
+augraphy