| Benchmark | Model | Rank | Results |
|---|---|---|---|
| audio-visual-speech-recognition-on-lrs3-ted | EG-seq2seq | #11 | Word Error Rate (WER): 6.8 |
| lipreading-on-lip-reading-in-the-wild | 3D Conv + P3D-ResNet50 + TCN | #13 | Top-1 Accuracy: 84.80 |
| lipreading-on-lrs3-ted | EG-seq2seq | #14 | Word Error Rate (WER): 57.8 |