pyannote/speaker-diarization-3.1
AI model · https://huggingface.co/pyannote/speaker-diarization-3.1
First seen by Oriel on .
AI summary
pyannote/speaker-diarization-3.1 is an open-source PyTorch pipeline for automatic speaker diarization that removes the earlier pipeline’s use of onnxruntime.
- It requires pyannote.audio version 3.1 or higher and accepts mono audio sampled at 16 kHz, automatically downmixing multichannel audio and resampling other rates.
- The pipeline produces a pyannote Annotation instance, which can be written to disk in RTTM format.
- Users can run inference on a GPU, pass preloaded waveforms from memory, and monitor progress with ProgressHook.
- Speaker counts can be specified with num_speakers or bounded using min_speakers and max_speakers.
- Its benchmark uses fully automatic processing without dataset-specific tuning, with no forgiveness collar and overlapped speech included in DER evaluation.
#speaker diarization #pytorch #audio processing
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Likes
Total likes reported by the source.
- Hugging Face Models: 5,257, latest observation ; +201 over observed period since
Downloads (30d)
Rolling 30-day downloads. A change in this value is not new downloads during the observed period.
- Hugging Face Models: 6,393,366, latest observation ; -377,226 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Models | pyannote/speaker-diarization-3.1 | https://huggingface.co/pyannote/speaker-diarization-3.1 Read discussion |