---
language:
- ms
- en
---

# Malaysian-Podcast-Dia-1.6B

Full parameter finetuning [nari-labs/Dia-1.6B](https://huggingface.co/nari-labs/Dia-1.6B) on Malaysian Podcast from [mesolitica/Malaysian-Emilia](https://huggingface.co/datasets/mesolitica/Malaysian-Emilia) where the permutation for voice conversion only select 80% similar.

Complete tutorial how to use at [mesolitica/malaya-speech/Dia-TTS](https://github.com/mesolitica/malaya-speech/wiki/Dia%E2%80%90TTS).

## How we trained it

1. The finetuning done in FP32-BF16 mixed precision training.
2. Multipacking encoder-decoder.
3. Wandb at https://wandb.ai/huseinzol05/dia-tts-malaysian-emilia-full-mixed-precision-podcast

## Source code

Source code at https://github.com/mesolitica/malaya-speech/tree/master/session/dia-tts

## Acknowledgement

Special thanks to https://www.sns.com.my and Nvidia for 8x H100 node!