Automatic Speech Recognition on MLS Portuguese
14.39Relative WERUfal-Whisper
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Ufal-WhisperModel Size=large-v2, Chunk Size=300 msec, Initial Chunk Size=600 msec2025.08 | 14.39 | 14.26 | 11.85 | |
| WhisperRTModel Size=large-v2, Chunk Size=300 msec, Initial Chunk Size=600 msec2025.08 | 18.26 | 20.19 | 16.49 | |
| Simul-WhisperModel Size=large-v2, Chunk Size=300 msec, Initial Chunk Size=600 msec2025.08 | 18.44 | 22.15 | 17.16 |