Visual Speech Recognition on Multilingual TEDx-Spanish (MTes) (test)
56.6Mean WER
VSR model with prediction-based auxiliary tasks
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| 56.6 | 0.3 | 56.3 | ||
| 56.9 | 0.5 | 56.5 | ||
| 60.8 | 0.8 | 60.3 | ||
2022.02 | 66.4 | 0.8 | 65.2 |
VSR model with prediction-based auxiliary tasks
| Method | Links | |||
|---|---|---|---|---|
| 56.6 | 0.3 | 56.3 | ||
| 56.9 | 0.5 | 56.5 | ||
| 60.8 | 0.8 | 60.3 | ||
2022.02 | 66.4 | 0.8 | 65.2 |