---
license: cc-by-nc-4.0
pipeline_tag: text-to-speech
library_name: f5-tts
datasets:
- amphion/Emilia-Dataset
---
### 2024/10/14. We change the License of this ckpt repo to CC-BY-NC-4.0 following the used training set Emilia, which is an in-the-wild dataset. Sorry for any inconvenience this may cause. Our codebase remains under the MIT license.

Download [F5-TTS](https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_Base) or [E2 TTS](https://huggingface.co/SWivid/E2-TTS/tree/main/E2TTS_Base) and place under ckpts/
```
ckpts/
    E2TTS_Base/
        model_1200000.pt
    F5TTS_Base/
        model_1200000.pt
```
Inference with .safetensors option
```
ckpts/
    E2TTS_Base/
        model_1200000.safetensors
    F5TTS_Base/
        model_1200000.safetensors
```
Github: https://github.com/SWivid/F5-TTS      
Paper: [E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS](https://huggingface.co/papers/2406.18009)