SAVRN
Search Contact SAVRN

Open-weight model · Speech recognition

speaker-diarization-community-1

by Pyannote pyannote/speaker-diarization-community-1

This pipeline ingests mono audio sampled at 16kHz and outputs speaker diarization. - stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels.

Parameters—
Context—
Weights32.8 MB
Licensecc-by-4.0
AccessAccess requested at publisher
Monthly Downloads5.2M

SAVRN's Notes on speaker-diarization-community-1

Feed it mono audio at 16 kHz and it hands back who spoke when. The exclusive speaker diarization mode lines speaker turns up with transcription timestamps, so it sits ahead of whatever transcribes. The weights total about 33 MB across 10 files and the page shows no memory figure; the real sizing question is how many hours of audio a day you need diarized, not which card holds the model.

Credit the creator and indicate your changes, and CC BY 4.0 permits commercial use and adaptation. Access is gated, so the publisher's terms come before the files do. What to check: the publisher offers optional hosting on pyannoteAI cloud, but offline use is what keeps audio on your own floor, and the page lists four papers describing it, the third DIHARD challenge and AVA-AVD among them, worth reading before you commit.

SAVRN Research, 2026-09-18

Model Card

By Pyannote, published under cc-by-4.0, revision 3533c8cf8e36.

community-1 speaker diarization

This pipeline ingests mono audio sampled at 16kHz and outputs speaker diarization.

  • stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels.
  • audio files sampled at a different rate are resampled to 16kHz automatically upon loading.

The main improvements brought by Community-1 are:

  • improved speaker assignment and counting
  • simpler reconciliation with transcription timestamps with exclusive speaker diarization
  • easy offline use (i.e. without internet connection)
  • (optionally) hosted on pyannoteAI cloud

Setup

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

Quick start

# download the pipeline from Huggingface
from pyannote.audio import Pipeline
pipeline = Pipeline.from_pretrained(
    "pyannote/speaker-diarization-community-1", 
    token="{huggingface-token}")

# run the pipeline locally on your computer
output = pipeline("audio.wav")

# print the predicted speaker diarization 
for turn, speaker in output.speaker_diarization:
    print(f"{speaker} speaks between t={turn.start:.3f}s and t={turn.end:.3f}s")

Benchmark

Out of the box, Community-1 is much better than speaker-diarization-3.1.

Read the full model card (672 words)

Identity and Version

Repository
pyannote/speaker-diarization-community-1
Publisher
Pyannote
Task
Speech recognition
Modality
Audio
Library
pyannote-audio
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
3533c8cf8e369892e6b79ff1bf80f7b0286a54ee
First published
2025-04-15
Last updated
2025-09-29

Files and Weights

10 files, 33.7 MB in total. The weights are 4 files totalling 32.8 MB in bin, npz.

Weights4 files · 32.8 MB
Configuration1 file · 444 B
Documentation3 files · 11.1 KB
Other1 file · 861.4 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
embedding/pytorch_model.binWeights26.6 MB —
plda/plda.npzWeights133.9 KB —
plda/xvec_transform.npzWeights134.4 KB —
segmentation/pytorch_model.binWeights5.9 MB —
config.yamlConfiguration444 B —
README.mdDocumentation10.0 KB —
embedding/README.mdDocumentation938 B —
plda/README.mdDocumentation220 B —
diarization.gifOther861.4 KB —
.gitattributesRepository1.6 KB —

License and Download

License
cc-by-4.0
Access
Access requested at publisher
Download size
32.8 MB
Request access from Pyannote

Pyannote grants access through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published32.8 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About speaker-diarization-community-1

Can I use speaker-diarization-community-1 commercially?

Yes. speaker-diarization-community-1 is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated.

Similar Models

Model · Speech recognition

wav2vec2-large-xlsr-53-japanese

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the train and validation splits of Common Voice 6.1, CSS10 and JSUT. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: The model can be evaluated as follows on the Japanese test data of Common Voice. In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the…

Open weights apache-2.0 transformers
View model

Model · Speech recognition

whisperkit-coreml

Argmax

WhisperKit is part of Argmax OSS, an On-device Speech AI SDK for Apple Silicon: https://github.com/argmaxinc/argmax-oss-swift Check out the WhisperKit paper and presentation from ICML 2025: https://icml.cc/virtual/2025/47854 For real-time transcription with speakers and custom vocabulary, check out Argmax Pro SDK: https://www.argmaxinc.com/blog/argmax-sdk-2

Open weights mit whisperkit
View model

Model · Speech recognition

speaker-diarization-3.1

Pyannote

Using this open-source model in production? Consider switching to pyannoteAI for better and faster options. This pipeline is the same as pyannote/speaker-diarization-3.0 except it removes the problematic use of onnxruntime. Both speaker segmentation and embedding now run in pure PyTorch. This should ease deployment and possibly speed up inference. It requires pyannote.audio version 3.1 or higher. It ingests mono audio sampled at 16kHz and outputs speaker diarization as an Annotation instance: - stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels. - audio files sampled at a different rate are resampled to 16kHz automatically upon loading. 1.…

Access requested at publisher mit pyannote-audio
View model

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Portuguese using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: 1. To evaluate on mozilla-foundation/commonvoice60 with split test 2. To evaluate on speech-recognition-community-v2/devdata If you want to cite this model you can use this

Open weights apache-2.0 transformers
View model

Model · Speech recognition

wav2vec2-large-xlsr-53-russian

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Russian using the train and validation splits of Common Voice 6.1 and CSS10. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: 1. To evaluate on mozilla-foundation/commonvoice60 with split test 2. To evaluate on speech-recognition-community-v2/devdata If you want to cite this model you can use this

Open weights apache-2.0 transformers
View model

Model · Speech recognition

wav2vec2-large-xlsr-53-polish

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Polish using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: 1. To evaluate on mozilla-foundation/commonvoice60 with split test 2. To evaluate on speech-recognition-community-v2/devdata If you want to cite this model you can use this

Open weights apache-2.0 transformers
View model