PyPI page
Home page
Author:
Max Bain
License:
BSD-2-Clause
Summary:
Time-Accurate Automatic Speech Recognition using Whisper.
Latest version:
3.8.5
Required dependencies:
ctranslate2
|
faster-whisper
|
huggingface-hub
|
nltk
|
numpy
|
omegaconf
|
pandas
|
pyannote-audio
|
torch
|
torchaudio
|
torchcodec
|
torchvision
|
transformers
|
triton
Optional dependencies:
pytest
Downloads last day:
35,237
Downloads last week:
222,872
Downloads last month:
1,038,242