Landmark Based Lipreading On Lrs2
评估指标
Word Error Rate (WER)
评测结果
各个模型在此基准测试上的表现结果
模型名称 | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|
| SyncVSR | 74.6 | SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization |
0 of 1 row(s) selected.