metadata
language:
- ms
- en
Malaysian Distil Whisper Large V3
Distil Whisper Large V3 on Malaysian dataset,
- IMDA STT, https://huggingface.co/datasets/mesolitica/IMDA-STT
- Pseudolabel Malaysian youtube videos, https://huggingface.co/datasets/mesolitica/pseudolabel-malaysian-youtube-whisper-large-v3
We follow exact distillation process from https://github.com/huggingface/distil-whisper with minor changes.
Script at https://github.com/mesolitica/malaya-speech/tree/malaysian-speech/session/distill-whisper
Wandb at https://wandb.ai/huseinzol05/distil-whisper?workspace=user-huseinzol05