mesolitica
/

Malaysian-sesame-csm-1b

Model card Files Files and versions

Metrics Training metrics Community

Malaysian-Sesame-csm-1B

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

How we trained it

The finetuning done in FP32-BF16 mixed precision training.
Multipacking decoder.
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!

Downloads last month: 31

Safetensors

Model size

1.55B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including mesolitica/Malaysian-sesame-csm-1b

Malaysian Text-to-Speech

Malaysian Text-to-Speech models. • 21 items • Updated Jun 24 • 2