PyPI page
Home page
Author:
gitcommitshow
Summary:
Speech-To-Text pipeline supporting all OpenAI-compatible Automatic Speech Recognition providers with added resilience and metadata through LLM-powered transcript repair, audio preprocessing, vad, and pyannote diarization
Latest version:
0.4.3
Required dependencies:
httpx
|
numpy
|
pyannote.audio
|
pydantic
|
python-dotenv
|
soundfile
|
torch
|
webrtcvad
Optional dependencies:
pytest
|
silero-vad
Downloads last day:
2
Downloads last week:
56
Downloads last month:
293