PyPI page
Home page
Author:
miguelvalente
License:
Summary:
Go from raw audio to a text-audio dataset with OpenAI's Whisper
Latest version:
0.1.7
Required dependencies:
ffmpeg-python
|
jupyter
|
librosa
|
numpy
|
openai-whisper
|
pyannote-audio
|
pydub
|
scipy
|
torch
|
torchaudio
|
tqdm
|
transformers
|
typer
Downloads last day:
6
Downloads last week:
72
Downloads last month:
243