Name: segmentation
Author: pyannote

Overview

The pyannote segmentation model is a specialized tool for Voice Activity Detection (VAD) and speaker change detection. Unlike general-purpose ASR models, this model focuses on the temporal boundaries of speech, allowing developers to precisely isolate voice segments from background noise or identify transitions between different speakers in a recording. It is particularly effective for preprocessing pipelines where accurate timestamping is required before passing audio to a transcription engine. With an MIT license, it offers high flexibility for commercial integration. Developers can deploy it as a lightweight frontend to reduce computational overhead by stripping silent intervals from long-form audio streams.

Highlights

Precise voice activity detection and speaker change tracking
MIT licensed for flexible commercial and open-source use
Optimizes ASR pipelines by removing non-speech intervals
Lightweight preprocessing for long-form audio stream analysis

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("pyannote/segmentation")
tokenizer = AutoTokenizer.from_pretrained("pyannote/segmentation")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download pyannote/segmentation

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download pyannote/segmentation config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('pyannote/segmentation')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/pyannote/segmentation

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/pyannote/segmentation

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('pyannote/segmentation')
tokenizer = AutoTokenizer.from_pretrained('pyannote/segmentation')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model pyannote/segmentation

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model pyannote/segmentation README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('pyannote/segmentation')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/pyannote/segmentation.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/pyannote/segmentation.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'pyannote/segmentation')