Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

The collected information will help acquire a better knowledge of pyannote.audio userbase and help its maintainers improve it further. Though this model uses MIT license and will always remain open-source, we will occasionnally email you about premium models and paid services around pyannote.

Log in or Sign Up to review the conditions and access this model content.

Using this open-source model in production?
Make the most of it thanks to our consulting services.

🎹 "Powerset" speaker segmentation

This model ingests 10 seconds of mono audio sampled at 16kHz and outputs speaker diarization as a (num_frames, num_classes) matrix where the 7 classes are non-speech, speaker #1, speaker #2, speaker #3, speakers #1 and #2, speakers #1 and #3, and speakers #2 and #3.

Example output

# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
multilabel_encoding = to_multilabel(powerset_encoding)

The various concepts behind this model are described in details in this paper.

It has been trained by Séverin Baroudi with pyannote.audio 3.0.0 using the combination of the training sets of AISHELL, AliMeeting, AMI, AVA-AVD, DIHARD, Ego4D, MSDWild, REPERE, and VoxConverse.

This companion repository by Alexis Plaquet also provides instructions on how to train or finetune such a model on your own data.


  1. Install pyannote.audio 3.0 with pip install pyannote.audio
  2. Accept pyannote/segmentation-3.0 user conditions
  3. Create access token at hf.co/settings/tokens.


# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(

Speaker diarization

This model cannot be used to perform speaker diarization of full recordings on its own (it only processes 10s chunks).

See pyannote/speaker-diarization-3.0 pipeline that uses an additional speaker embedding model to perform full recording speaker diarization.

Voice activity detection

from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions

Overlapped speech detection

from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions


  author={Alexis Plaquet and Hervé Bredin},
  title={{Powerset multi-class cross entropy loss for neural speaker diarization}},
  booktitle={Proc. INTERSPEECH 2023},
  author={Hervé Bredin},
  title={{pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe}},
  booktitle={Proc. INTERSPEECH 2023},
Downloads last month
Inference API (serverless) has been turned off for this model.

Spaces using pyannote/segmentation-3.0 9