Speech Representation Evaluation on VoxCeleb 1 (test)
876.1SUPERB ScoreSpeech-FT
Evaluation Results
| Method | Links | |
|---|---|---|
| Speech-FTFine-tuning Source=English (mono-lingual)2025.02 | 876.1 | |
| Pre-trainedNote=Original HuBERT model2025.02 | 870.2 | |
| Speech-FTFine-tuning Source=Spanish (cross-lingual)2025.02 | 868.26 | |
| Stable-FTFine-tuning Source=English (mono-lingual)2025.02 | 867.96 | |
| Speech-FTFine-tuning Source=Chinese (cross-lingual)2025.02 | 866.51 | |
| Stable-FT (20%)Fine-tuning Source=Chinese (cross-lingual), Snapshot=20% of total fine-tuning steps2025.02 | 832.37 | |
| Stable-FTFine-tuning Source=Chinese (cross-lingual)2025.02 | 789.88 | |
| Stable-FTFine-tuning Source=Spanish (cross-lingual)2025.02 | 747.5 |