Automatic Speech Recognition on TIMIT
1.29WERCrisperWhisper
Evaluation results
| Method | Links | |
|---|---|---|
| CrisperWhisper2026.04 | 1.29 | |
| Mixed Training + Length Aug + Timestamp RegLength Augmentation=true, Timestamp Regularization=true, Evaluation Setting=zero-shot2026.04 | 2.53 | |
| ASR-only BaselineEvaluation Setting=zero-shot2026.04 | 2.85 | |
| Mixed Training + Length Aug + Reduced TFLength Augmentation=true, Reduced Teacher Forcing=true, Evaluation Setting=zero-shot2026.04 | 3.04 | |
| Mixed TrainingEvaluation Setting=zero-shot2026.04 | 3.13 | |
| Mixed Training + Length AugLength Augmentation=true, Evaluation Setting=zero-shot2026.04 | 4.18 | |
| Qwen-Audio2026.04 | 5.96 |