Oriel — AI & technology worth noticing, every day.

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

SourceExternal IDURL
Hugging Face Modelspyannote/speaker-diarization-3.1https://huggingface.co/pyannote/speaker-diarization-3.1 Read discussion