Name: brouhaha
Author: pyannote

Overview

Brouhaha is a specialized voice activity detection (VAD) model developed by pyannote, designed to distinguish human speech from background noise in real-time or batch audio streams. For developers building voice-enabled applications, this model serves as a critical pre-processing layer, allowing you to trigger downstream ASR (Automatic Speech Recognition) or diarization pipelines only when actual speech is detected. This significantly reduces computational overhead and API costs by filtering out silence and non-speech interference. Integration is straightforward for those already using the pyannote ecosystem, providing a lightweight, high-precision alternative to generic energy-based thresholding. It is released under the OpenRAIL license, making it suitable for a wide range of commercial and open-source deployments.

Highlights

High-precision speech vs. noise discrimination
Reduces downstream ASR computational costs
Seamless integration with pyannote audio pipelines
OpenRAIL license for flexible commercial deployment
Optimized for real-time voice activity triggering

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/brouhaha")
tokenizer = AutoTokenizer.from_pretrained("pyannote/brouhaha")

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/brouhaha

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

huggingface-cli download pyannote/brouhaha 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/brouhaha')

Git Download

Make sure git-lfs is installed first

Git Download

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

To skip LFS large-file downloads, use:

Skip LFS

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

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/brouhaha')
tokenizer = AutoTokenizer.from_pretrained('pyannote/brouhaha')

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/brouhaha

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

modelscope download --model pyannote/brouhaha 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/brouhaha')

Git Download

Make sure git-lfs is installed first

Git Download

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

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/pyannote/brouhaha.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/brouhaha')