---
title: README
emoji: 🚀
colorFrom: yellow
colorTo: green
sdk: static
pinned: false
---

[**pyannote.audio**](https://github.com/pyannote/pyannote-audio) is an open-source toolkit for speaker diarization.

Pretrained pipelines reach state-of-the-art performance on most academic benchmarks and are used [in production by dozens of companies](https://herve.niderb.fr/consulting.html).

| Benchmark             | v1.1 | [v2.1](https://hf.co/pyannote/speaker-diarization-2.1) | [v3.1](https://hf.co/pyannote/speaker-diarization-3.1) |  <a href="mailto:herve-at-niderb-dot-fr?subject=Premium pyannote.audio pipeline&body=Looks like I got your attention! Drop me an email for more details. Hervé.">Premium</a>  |
| ---------------------- | ---- | ------ | ------ | --------- |
| AISHELL-4              | -    |  14.1  |  12.2  | 11.9      |
| AliMeeting (channel 1) | -    |  27.4  |  24.4  | 22.5      |
| AMI (IHM)              | 29.7 |  18.9  |  18.8  | 16.6      |
| AMI (SDM)              | -    |  27.1  |  22.4  | 20.9      |
| AVA-AVD                | -    |  -     |  50.0  | 39.8      |
| DIHARD 3 (full)        | 29.2 |  26.9  |  21.7  | 17.2      |
| MSDWild                | -    |  -     |  25.3  | 19.8      |
| REPERE (phase2)        | -    |   8.2  |   7.8  |  7.6      |
| VoxConverse (v0.3)     | 21.5 |  11.2  |  11.3  |  9.4      |
[Diarization error rate](http://pyannote.github.io/pyannote-metrics/reference.html#diarization) (in %)

Using one Nvidia Tesla V100 SXM2 GPU and one Intel Cascade Lake 6248 CPU,
* [v2.1](https://hf.co/pyannote/speaker-diarization-2.1) takes around 1m30s to process 1h of audio
* [v3.1](https://hf.co/pyannote/speaker-diarization-3.1) takes around 1m20s to process 1h of audio
* <a href="mailto:herve-at-niderb-dot-fr?subject=Premium pyannote.audio pipeline&body=Looks like I got your attention! Drop me an email for more details. Hervé.">Premium</a> takes less than 1m00s to process 1h of audio