Automatic Speech Recognition Asr On Lrs3 Ted
Metriken
Word Error Rate (WER)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|
| CTC/Attention | 1 | Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels | |
| DistillAV | - | Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models |
0 of 2 row(s) selected.