Visual Speech Recognition on LRS3-TED

Metric: Word Error Rate (WER) (lower is better)

LeaderboardDataset
Loading chart...
#ModelWord Error Rate (WER)Extra DataPaperDateCode
1CTC/Attention19.1YesAuto-AVSR: Audio-Visual Speech Recognition with ...2023-03-25Code
2VTP with more data30.7YesSub-word Level Lip Reading With Visual Attention2021-10-14-
3VTP40.6YesSub-word Level Lip Reading With Visual Attention2021-10-14-