metadata
language:
- ms
- en
Malaysian-Podcast-Dia-1.6B
Full parameter finetuning nari-labs/Dia-1.6B on Malaysian Podcast from mesolitica/Malaysian-Emilia where the permutation for voice conversion only select 80% similar.
Complete tutorial how to use at mesolitica/malaya-speech/Dia-TTS.
How we trained it
- The finetuning done in FP32-BF16 mixed precision training.
- Multipacking encoder-decoder.
- 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!