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) |
|---|---|
| whisper-flamingo-integrating-visual-features | 0.68 |
| jointly-learning-visual-and-auditory-speech | 1.4 |
| large-language-models-are-strong-audio-visual | 0.81 |
| learning-audio-visual-speech-representation-1 | 1.3 |