whisper-transcribe-new / requirements.txt
liuyang
add upload
06b904d
raw
history blame contribute delete
704 Bytes
# 1. Do NOT pin torch/torchaudio here – keep the CUDA builds that come with the image
transformers==4.48.0
# Removed flash-attention since faster-whisper handles this internally
# https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.0.8/flash_attn-2.7.4.post1+cu126torch2.4-cp310-cp310-linux_x86_64.whl
pydantic==2.10.6
# 2. Main whisper model
faster-whisper==1.1.1
ctranslate2==4.5.0
torch
# 3. Extra libs your app really needs
gradio==5.0.1
spaces>=0.19.0
pyannote.audio==3.3.1
pandas>=1.5.0
numpy<1.24.0
librosa>=0.10.0
soundfile>=0.12.0
ffmpeg-python>=0.2.0
requests>=2.28.0
nvidia-cudnn-cu12==9.1.0.70 # any 9.1.x that pip can find is fine
webrtcvad>=2.0.10
boto3