|
torch==1.13.0 |
|
opencv-python==4.7.0.72 |
|
Pillow==9.5.0 |
|
openai-whisper==20230314 |
|
gradio==3.28.1 |
|
transformers==4.28.0 |
|
diffusers==0.15.1 |
|
controlnet_aux |
|
langchain==0.0.101 |
|
decord==0.6.0 |
|
openai==0.27.4 |
|
ffmpeg-python==0.2.0 |
|
fairscale==0.4.3 |
|
lvis==0.5.3 |
|
suno-bark |
|
easyocr==1.6.2 |
|
easydict==1.9 |
|
scikit-learn==0.24.2 |
|
pytorch-lightning==1.5.10 |
|
albumentations==0.5.2 |
|
webdataset==0.2.48 |
|
kornia==0.5.0 |
|
sentencepiece==0.1.98 |
|
accelerate==0.18.0 |
|
git+https://github.com/facebookresearch/segment-anything.git |
|
git+https://github.com/facebookresearch/detectron2.git |