lucataco/speaker-diarization 🖼️ → 🖼️

▶️ 13.6K runs 📅 Jul 2023 ⚙️ Cog 0.8.1 🔗 GitHub ⚖️ License
audio-analysis audio-segmentation speaker-diarization

Performance

5.4sTypical run time
~185sCold start (first call)
13.6KTotal runs

About

Segments an audio recording based on who is speaking (on A100)

Example Output

Output

Example output

Performance Metrics

5.42s Prediction Time
185.42s Total Time
Input Parameters
audio Type: stringDefault: https://pyannote-speaker-diarization.s3.eu-west-2.amazonaws.com/lex-levin-4min.mp3
Audio file
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
pre-processing audio file...
diarizing audio file...
post-processing diarization...
Version Details
Version ID
718182bfdc7c91943c69ed0ac18ebe99a76fdde67ccd01fced347d8c3b8c15a6
Version Created
July 21, 2023
Run on Replicate →