mesolitica/Malaysian-sesame-csm-1b

Malaysian-Sesame-csm-1B

Full parameter finetuning sesame/csm-1b on mesolitica/Malaysian-Emilia.

How we trained it

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

Source code

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

Acknowledgement

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