Audio-Visual Speech Recognition on LRS3 433 h 0 dB SNR
1.7WERAVUR-LLM
Evaluation results
| Method | Links | |
|---|---|---|
| AVUR-LLMModality=AV2026.03 | 1.7 | |
| MMS-LLaMAModality=AV2026.03 | 2.7 | |
| AVGERModality=AV2026.03 | 3.7 | |
| Llama-AVSRModality=AV2026.03 | 4.2 | |
| CMAModality=AV2026.03 | 4.4 | |
| AV-HuBERTModality=AV2026.03 | 5.8 | |
| Whisper-FlamingoModality=AV2026.03 | 6.3 |