Automatic Speech Recognition on Buckeye (BUCK)
10.63WERCrisperWhisper
Evaluation results
| Method | Links | |
|---|---|---|
| CrisperWhisper2026.04 | 10.63 | |
| Mixed TrainingEvaluation Setting=zero-shot2026.04 | 11.51 | |
| Mixed Training + Length AugLength Augmentation=true, Evaluation Setting=zero-shot2026.04 | 11.84 | |
| Mixed Training + Length Aug + Timestamp RegLength Augmentation=true, Timestamp Regularization=true, Evaluation Setting=zero-shot2026.04 | 11.88 | |
| Mixed Training + Length Aug + Reduced TFLength Augmentation=true, Reduced Teacher Forcing=true, Evaluation Setting=zero-shot2026.04 | 12.07 | |
| ASR-only BaselineEvaluation Setting=zero-shot2026.04 | 12.09 | |
| Qwen-Audio2026.04 | 12.15 |