---
title: paraformer-seaco-large-zh-timestamp-onnx-offline
canonical_url: "https://www.modelscope.cn/models/manyeyes/paraformer-seaco-large-zh-timestamp-onnx-offline"
md_url: "https://www.modelscope.cn/models/manyeyes/paraformer-seaco-large-zh-timestamp-onnx-offline.md"
repository: manyeyes/paraformer-seaco-large-zh-timestamp-onnx-offline
chinese_name: "SeACoParaformer-large-语音识别-中文-热词-时间戳-离线-onnx模型"
last_updated: 2025-08-22
license: "Apache License 2.0"
pipeline_tag: auto-speech-recognition
tasks:
  - auto-speech-recognition
library_name:
  - onnx
  - pytorch
frameworks:
  - Pytorch
downloads: 1214
stars: 8
---

# paraformer-seaco-large-zh-timestamp-onnx-offline

> paraformer-seaco-large-zh-timestamp-onnx-offline - manyeyes 在 ModelScope 开源的模型。SeACoParaformer-large-语音识别-中文-热词-时间戳-离线-onnx模型

manyeyes/paraformer-seaco-large-zh-timestamp-onnx-offline 是 ModelScope 魔搭社区上的auto-speech-recognition模型，采用 Apache License 2.0 许可。

- **Repository**: manyeyes/paraformer-seaco-large-zh-timestamp-onnx-offline
- **License**: Apache License 2.0
- **Tasks**: auto-speech-recognition
- **Downloads**: 1214
- **Stars**: 8
- **Last updated**: 2025-08-22

Source: https://www.modelscope.cn/models/manyeyes/paraformer-seaco-large-zh-timestamp-onnx-offline

---

### 模型介绍
seaco-paraformer相较于clas把热词建模从asr decoder解耦出来了，通过两个后验概率的融合进行热词激励，可以更直观的看到热词的激励过程。并且seaco的热词建模部分使用了更多的参数，效果更好，这部分可以参考论文中的结果。
性能上因为增加的计算量在模型整体中较少，所以没有明显的性能损失。
#### 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('manyeyes/paraformer-seaco-large-zh-timestamp-onnx-offline')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/manyeyes/paraformer-seaco-large-zh-timestamp-onnx-offline.git
```

<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>