search

SYSTRAN / faster-whisper

Faster Whisper transcription with CTranslate2
MIT License
11.26k stars 939 forks source link

I can‘t find BatchedInferencePipeline. #935

Open ZHJ19970917 opened 1 month ago

ZHJ19970917 commented 1 month ago

faster_whisper == 1.0.3 from faster_whisper import WhisperModel, BatchedInferencePipeline

model = WhisperModel("medium", device="cuda", compute_type="float16") batched_model = BatchedInferencePipeline(model=model) segments, info = batched_model.transcribe("audio.wav", batch_size=16)

for segment in segments: print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

ImportError: cannot import name 'BatchedInferencePipeline' from 'faster_whisper'

zh-plus commented 1 month ago

The batched inference pull request has been merged but hasn't been published to PYPI yet. Try installing faster-whisper directly from the source:

pip install --force-reinstall "faster-whisper @ https://github.com/SYSTRAN/faster-whisper/archive/refs/heads/master.tar.gz"
piyushmaharana commented 1 month ago

websockets==12.0 speechbrain==1.0.0 pyannote.audio==3.2.0 asyncio==3.4.3 sentence-transformers==2.7.0 transformers==4.40.2 torchvision~=0.18.0 torch~=2.3.0 faster-whisper @ https://github.com/SYSTRAN/faster-whisper/archive/refs/heads/master.tar.gz

example requirements.txt file

greg2705 commented 2 weeks ago

Hello, Im wroking behind a proxy having only access to pypi,any ideas when the package update willl be upload on pypi ? Thanks !