WhisperSpeech / requirements.txt
Tonic's picture
Update requirements.txt
f350321 verified
raw
history blame
243 Bytes
torch
torchaudio
transformers
accelerate
fastcore
fastprogress
vocos
speechbrain
soundfile
webdataset
vector_quantize_pytorch==1.6.22
openai-whisper
wandb
whisper_normalizer
jiwer
matplotlib
pandas
pyarrow
scikit-learn
ipython
whisperx
whisper