Malaysian Finetune Whisper Large V3 Turbo
Finetune Whisper Large V3 Turbo on Malaysian context.
Improvement
- Distilled from Whisper Large V3 on Malaysian and Science context.
- Better translation for Malay, Manglish, Mandarin, Tamil and Science context.
- Word level timestamp, introduced
<|transcribeprecise|>
token, a new task!
how we finetuned it?
We done 3 phases,
- Finetune on mesolitica/Malaysian-STT-Whisper
- Revision 267552e0f093068519a816112c2741939d057f48
- WanDB at https://wandb.ai/huseinzol05/malaysian-whisper-large-v3-turbo-v3
- Stage 2, Annealing on 5% from mesolitica/Malaysian-STT-Whisper and 100% from mesolitica/Malaysian-STT-Whisper-Stage2
- Revision 5f6ca0596f01527ec2d013662cfc168d5f754461
- WanDB at https://wandb.ai/huseinzol05/malaysian-whisper-large-v3-turbo-v3-stage2
- Stage 3, verified Malaysian Voice Conversion.
- Downloads last month
- 4,125
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support