---
title: F5-TTS_Emilia-ZH-EN
canonical_url: "https://www.modelscope.cn/models/SWivid/F5-TTS_Emilia-ZH-EN"
md_url: "https://www.modelscope.cn/models/SWivid/F5-TTS_Emilia-ZH-EN.md"
repository: SWivid/F5-TTS_Emilia-ZH-EN
last_updated: 2025-03-12
license: CC-BY-NC-4.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
parameters: 337.1M
tensor_type:
  - F32
  - BOOL
  - I64
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
downloads: 59410
stars: 42
---

# F5-TTS_Emilia-ZH-EN

> F5-TTS_Emilia-ZH-EN - SWivid 在 ModelScope 开源的模型。在Emilia中英10万小时数据上训练的F5-TTS，沿用模型训练使用数据集协议CC-BY-NC-4.0

SWivid/F5-TTS_Emilia-ZH-EN 是 ModelScope 魔搭社区上的 337.1M 参数text-to-speech模型，采用 CC-BY-NC-4.0 许可。

- **Repository**: SWivid/F5-TTS_Emilia-ZH-EN
- **License**: CC-BY-NC-4.0
- **Tasks**: text-to-speech
- **Parameters**: 337.1M
- **Downloads**: 59410
- **Stars**: 42
- **Last updated**: 2025-03-12

Source: https://www.modelscope.cn/models/SWivid/F5-TTS_Emilia-ZH-EN

---

Download [F5-TTS_Emilia-ZH-EN](https://www.modelscope.cn/models/SWivid/F5-TTS_Emilia-ZH-EN/files) or [E2-TTS_Emilia-ZH-EN](https://www.modelscope.cn/models/SWivid/E2-TTS_Emilia-ZH-EN/files) and place under ckpts/
```
ckpts/
    F5TTS_v1_Base/
        model_1250000.safetensors
```
Github: https://github.com/SWivid/F5-TTS      
Paper: [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://arxiv.org/abs/2410.06885)
#### 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
pip install modelscope
```
```python
from modelscope import snapshot_download
model_dir = snapshot_download('F5-TTS_Emilia-ZH-EN')
```
Git下载
```
git clone https://www.modelscope.cn/SWivid/F5-TTS_Emilia-ZH-EN.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>