PyPI page
Home page
Summary:
Multi-source speech transcription with LLM-based adjudication inspired by textual criticism
Latest version:
1.5.2
Required dependencies:
anthropic
|
mlx-whisper
|
numpy
|
openai
|
openai-whisper
|
tomli
|
yt-dlp
Optional dependencies:
datasets
|
meeteval
|
mlx-audio
|
parakeet-mlx
|
pyannote-audio
|
pytest
|
soundfile
Downloads last day:
1
Downloads last week:
30
Downloads last month:
73
7-day smoothing