Visual Text-to-Speech on LRS2 zero-shot
8.93WERGT
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GTType=GT2026.06 | 8.93 | 100 | 3.14 | 7.59 | |
| Foley-OmniType=Text+Video2026.06 | 13 | 64.6 | 2.67 | 8.24 | |
| LipVoicerType=Video2026.06 | 22.5 | 62.1 | 2.16 | 9.52 | |
| Faces2VoicesType=Video2026.06 | 31.5 | 65 | 3.88 | 8.26 | |
| EmoDubberType=Text+Video2026.06 | 110 | 10.3 | 1.7 | 8.68 |