Automatic Speech Recognition on MLS German
13.83Relative WERUfal-Whisper
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Ufal-WhisperModel Size=large-v2, Chunk Size=300 msec, Initial Chunk Size=600 msec2025.08 | 13.83 | 15.21 | 11.4 | |
| WhisperRTModel Size=large-v2, Chunk Size=300 msec, Initial Chunk Size=600 msec2025.08 | 14.07 | 17.54 | 14.45 | |
| Simul-WhisperModel Size=large-v2, Chunk Size=300 msec, Initial Chunk Size=600 msec2025.08 | 16.2 | 24.79 | 20.4 |