Automatic Speech Recognition on L2-ARCTIC created subset
11.67Error Rate (ZH)INTapt
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| INTaptBackbone=HUBERT XLarge, Updated Parameters=19.9M2023.05 | 11.67 | 6.63 | 18.41 | 7.17 | 10.44 | 10.55 | 11 | |
| PromptctcBackbone=HUBERT XLarge, Updated Parameters=19.7M2023.05 | 13.02 | 7.31 | 19.26 | 8.05 | 10.46 | 10.38 | 11.41 | |
| INTaptBackbone=HUBERT Large, Updated Parameters=12.9M2023.05 | 13.09 | 6.64 | 21.25 | 8.97 | 12.18 | 11.92 | 12.34 | |
| PromptctcBackbone=HUBERT Large, Updated Parameters=12.5M2023.05 | 13.93 | 7.2 | 21.93 | 9.69 | 12.64 | 12.38 | 12.96 | |
| FinetuneBackbone=HUBERT Large, Updated Parameters=315M2023.05 | 15.46 | 7.91 | 22.26 | 9.95 | 14.19 | 13.94 | 13.95 | |
| FinetuneBackbone=HUBERT XLarge, Updated Parameters=958M2023.05 | 15.49 | 7.53 | 24.09 | 10.02 | 13.48 | 12.56 | 13.86 | |
| BackboneBackbone=HUBERT XLarge, Updated Parameters=02023.05 | 17.03 | 7.48 | 26.02 | 10.49 | 13.65 | 13.52 | 14.69 | |
| BackboneBackbone=HUBERT Large, Updated Parameters=02023.05 | 18.71 | 8.8 | 25.8 | 10.98 | 14.12 | 14.92 | 15.55 |