Voice: speakers and sound

WeSpeaker

A set of ready-made voiceprint models: checks whether the same person speaks in two recordings and helps split a recording by speaker. One of the models is built into pyannote 3.x.

Developer
WeNet community, China
First release
Nov 2022
Latest release
Jul 2026
Sizes
from a few to tens of millions of parameters
License
Commercial use allowedCode Apache 2.0; weights CC-BY 4.0 (VoxCeleb) and Apache 2.0 (CN-Celeb)
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Finance, Security, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • Voice verification of a customer during a call
  • Finding repeat calls from the same person
  • Splitting a recording by speaker

Where it is used

Banking and insuranceCall centersSecurity teams

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. ReDimNet2
  2. Модели на HF (ResNet, ECAPA, CAM++)
  3. WeSpeaker 1.2
  4. WeSpeaker 1.0

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can WeSpeaker be used in a commercial project?

Yes. License: Code Apache 2.0; weights CC-BY 4.0 (VoxCeleb) and Apache 2.0 (CN-Celeb). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does WeSpeaker need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does WeSpeaker support Russian?

Language does not matter for this model: it does not work with text.

Where can I download WeSpeaker and what does it cost?

The WeSpeaker weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Comparisons

Similar models

Voice: speakers and soundpyannote (диаризация)pyannoteAI (Hervé Bredin) · FranceCommercial use allowed

The most widely used open tool for splitting a recording by speaker: who spoke and when. Usually paired with speech recognition. Weights are issued after a short form on HF.

DetailsVoice: speakers and soundNVIDIA Sortformer / TitaNetNVIDIA · USACommercial use with conditions

NVIDIA models for "who is speaking": TitaNet recognizes a specific person's voice, Sortformer splits a recording into up to 4 speakers, including live during a call.

Details

Source: huggingface.co/api/models?author=Wespeaker. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.