Automatic Speech Recognition on Kannada Medical Domain Database
25.4WER (%)Hybrid Learnable + KenLM
Evaluation results
| Method | Links | |
|---|---|---|
| Hybrid Learnable + KenLMBackbone=Wav2Vec2, Evaluation Protocol=Fine-tuned2026.04 | 25.4 | |
| Hybrid Learnable + mT5Backbone=Wav2Vec2, Evaluation Protocol=Fine-tuned2026.04 | 27.3 | |
| Hybrid Learnable + IndicBARTBackbone=Wav2Vec2, Evaluation Protocol=Fine-tuned2026.04 | 27.7 | |
| Hybrid Learnable ConfidenceBackbone=Wav2Vec2, Evaluation Protocol=Fine-tuned2026.04 | 28.1 |