---
datasets:
- mesolitica/Malaysian-Emilia
language:
- ms
- en
base_model:
- SWivid/F5-TTS
---

# Full Parameter Finetuning Malaysian Emilia F5-TTS

Continue training from [SWivid/F5-TTS](https://huggingface.co/SWivid/F5-TTS) on [Malaysian-Emilia](https://huggingface.co/datasets/mesolitica/Malaysian-Emilia)

This model should be able to zero-shot voice conversion any Malaysian and Singaporean speakers.

WanDB at https://wandb.ai/huseinzol05/CFM-TTS, **still on training**.

## Dataset

We train on postfilter [Malaysian-Emilia](https://huggingface.co/datasets/mesolitica/Malaysian-Emilia) called [Malaysian-Voice-Conversion](https://huggingface.co/datasets/mesolitica/Malaysian-Voice-Conversion)

## Source code

All source code at https://github.com/mesolitica/malaya-speech/tree/master/session/f5-tts