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
- Malay Conversational Speech Corpus, https://huggingface.co/datasets/malaysia-ai/malay-conversational-speech-corpus
- Haqkiem TTS Dataset, this is private, but you request access from https://www.linkedin.com/in/haqkiem-daim/
- Pseudolabel Nusantara audiobooks, https://huggingface.co/datasets/mesolitica/nusantara-audiobook
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
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.