DeepSound-V1 / requirements.txt
lym0302
torch
522cede
torch==2.4.0
torchvision
torchaudio
python-dotenv
cython
gitpython >= 3.1
tensorboard >= 2.11
numpy==1.26.4
Pillow >= 9.5
opencv-python >= 4.8
scipy >= 1.7
tqdm >= 4.66.1
gradio >= 3.34
einops >= 0.6
hydra-core >= 1.3.2
requests
torchdiffeq
librosa==0.11.0
nitrous-ema
safetensors
auraloss
hydra_colorlog
tensordict
colorlog
open_clip_torch
soundfile
av
###############
accelerate==0.26.1
deepspeed==0.13.1
bitsandbytes==0.43.0
loralib
prodigyopt
tensorboard
torchmetrics==0.11.4
torch_audiomentations
asteroid==0.7.0
auraloss
torch_log_wmse
diffusers==0.25.1
transformers==4.42.3
tokenizers==0.19.1
sentencepiece==0.1.99
peft==0.4.0
imageio==2.34.0
imageio-ffmpeg==0.4.9
decord==0.6.0
moviepy==1.0.3
pysubs2
#scikit-learn==1.2.2
scikit-learn==1.6.1
matplotlib
tabulate
shortuuid
markdown2[all]
soundfile==0.12.1
#pyaudio
demucs==4.0.0
#audiomentations==0.24.0
pedalboard~=0.8.1
spafe==0.3.2
xformers
einops==0.8.1
einops-exts==0.0.4
rotary_embedding_torch==0.3.5
segmentation_models_pytorch
hyper_connections==0.1.11
omegaconf==2.2.3
beartype==0.14.1
pydantic>=2.0
protobuf==3.20.3
fastapi
uvicorn
httpx==0.24.1
requests
openai
gradio==3.50.0
gradio_client==0.6.1
spaces==0.29.2
pandas
scipy
tqdm==4.66.1
wandb
keyboard
ml_collections
pytorchvideo
imagebind @ git+https://github.com/hkchengrex/ImageBind.git
laion-clap @ git+https://github.com/hkchengrex/CLAP.git
hear21passt
msclap @ git+https://github.com/hkchengrex/MS-CLAP.git