Text-to-Audio
Inference Endpoints
TangoFlux / requirements.txt
hungchiayu's picture
Create requirements.txt
de28e55 verified
raw
history blame
164 Bytes
torch==2.4.0
torchaudio==2.4.0
torchlibrosa==0.1.0
torchvision==0.19.0
transformers==4.44.0
diffusers==0.30.0
accelerate==0.34.2
datasets==2.21.0
librosa
tqdm
wandb