mesolitica/Malaysian-F5-TTS-v2

Full Parameter Finetuning Malaysian Emilia F5-TTS v2

Continue training from SWivid/F5-TTS on Malaysian-Emilia,

with total 8472 hours included 600 hours Mandarin sampled from amphion/Emilia-Dataset.

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

Checkpoints

We uploaded full checkpoints with optimizer states at checkpoints.

Dataset

We train on postfilter Malaysian-Emilia called Malaysian-Voice-Conversion

Source code

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