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
Run time and cost
This model costs approximately $0.14 to run on Replicate, or 7 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 146 seconds. The predict time for this model varies significantly based on the inputs.