Automatic Speech Recognition on SUPERB 24kHz
6.35WERMSRHuBERT
Evaluation results
| Method | Links | |
|---|---|---|
| MSRHuBERTFine-tuning protocol=Single-rate2026.03 | 6.35 | |
| Re. 24kHz HuBERT BaseFine-tuning protocol=Single-rate2026.03 | 6.54 | |
| Re. 16kHz HuBERT BaseFine-tuning protocol=Single-rate2026.03 | 6.59 | |
| Re. 48kHz HuBERT BaseFine-tuning protocol=Single-rate2026.03 | 6.72 | |
| MSRHuBERTFine-tuning protocol=Mixed-rate2026.03 | 6.82 | |
| HuBERT BaseFine-tuning protocol=Single-rate2026.03 | 6.84 | |
| Re. 16kHz HuBERT BaseFine-tuning protocol=Mixed-rate2026.03 | 6.97 | |
| Re. 24kHz HuBERT BaseFine-tuning protocol=Mixed-rate2026.03 | 7.24 | |
| Re. 48kHz HuBERT BaseFine-tuning protocol=Mixed-rate2026.03 | 7.45 | |
| HuBERT BaseFine-tuning protocol=Mixed-rate2026.03 | 7.61 | |
| Re. 16kHz HuBERT Base (w/o resampling)Fine-tuning protocol=Mixed-rate, Resampling in fine-tuning=No2026.03 | 10.3 | |
| Re. 16kHz HuBERT Base (w/o resampling)Fine-tuning protocol=Single-rate, Resampling in fine-tuning=No2026.03 | 15.61 |