Automatic Speech Recognition (ASR) on LRS3-TED
Metric: WER (lower is better)
LeaderboardDataset
Loading chart...
Results
Submit a result| # | Model↕ | WER▲ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | DistillAV | 1.4 | No | Audio-Visual Representation Learning via Knowled... | 2025-02-09 | Code |
- 1.4WER· 2025-02-09