Visual Speech Recognition On Lrs3 Ted
Metrics
Word Error Rate (WER)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Word Error Rate (WER) |
|---|---|
| auto-avsr-audio-visual-speech-recognition | 19.1 |
| sub-word-level-lip-reading-with-visual | 40.6 |
| sub-word-level-lip-reading-with-visual | 30.7 |