Readme
This is similar to https://replicate.com/daanelson/whisperx
With two changes: - It uses the latest version of WhisperX, as of Oct 16 - It adds a flag to allow use of diarization via Pyannote 3.0
venkr
/
whisperx-diarization
Whisper-Large-V2 + Pyannote 3.0 diarization via WhisperX
Input
Output
Run time and cost
This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 146 seconds. The predict time for this model varies significantly based on the inputs.