Automatic Speech Recognition on Prospective Multi-Center Endoscopy Dataset (C5)
15.6CEREndoASR
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| EndoASRDescription=Domain-adapted model after stage-1 and stage-2 fine-tuning2026.04 | 15.6 | 84.97 | 91.9 | 68.48 | |
| EndoASR-noiseDescription=Domain-adapted model after stage-1 and stage-2 fine-tuning2026.04 | 16.89 | 83.64 | 91.36 | 70.45 | |
| ParaformerDescription=Baseline model2026.04 | 19.38 | 81.01 | 89.38 | 57.33 |