---
title: pyannote-audio
canonical_url: "https://www.modelscope.cn/models/pengzhendong/pyannote-audio"
md_url: "https://www.modelscope.cn/models/pengzhendong/pyannote-audio.md"
repository: pengzhendong/pyannote-audio
last_updated: 2024-09-04
license: "Apache License 2.0"
pipeline_tag: voice-activity-detection
tasks:
  - voice-activity-detection
library_name:
  - onnx
  - pytorch
frameworks:
  - Pytorch
downloads: 6128
stars: 2
---

# pyannote-audio

> pyannote-audio - pengzhendong 在 ModelScope 开源的模型。当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。

pengzhendong/pyannote-audio 是 ModelScope 魔搭社区上的voice-activity-detection模型，采用 Apache License 2.0 许可。

- **Repository**: pengzhendong/pyannote-audio
- **License**: Apache License 2.0
- **Tasks**: voice-activity-detection
- **Downloads**: 6128
- **Stars**: 2
- **Last updated**: 2024-09-04

Source: https://www.modelscope.cn/models/pengzhendong/pyannote-audio

---

### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。

#### 您可以通过如下 git clone 命令，或者 ModelScope SDK 来下载模型

SDK 下载

```bash
#安装ModelScope
pip install modelscope
```

```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('pengzhendong/pyannote-onnx')
```

Git 下载

```
#Git模型下载
git clone https://www.modelscope.cn/pengzhendong/pyannote-onnx.git
```

# Pyannote ONNX

- segmentation
  - from: https://huggingface.co/pyannote/segmentation
  - duration: 5.0
  - max_num_speakers: 3
- segmentaion-3.0
  - from: https://huggingface.co/pyannote/segmentation-3.0
  - duration: 10.0
  - max_speakers_per_chunk: 3
  - max_speakers_per_frame: 2
- segmentation_bigdata
  - from: https://github.com/HHousen/speaker-change-detection
  - duration: 5.0
  - max_num_speakers: 4
- short_scd_bigdata
  - from: https://github.com/HHousen/speaker-change-detection
  - duration: 5.0