📊 Showing 2 results | 📏 Metric: WER
| Rank | Model | Paper | WER | Date | Code |
|---|---|---|---|---|---|
| 1 | CTC/Attention | Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels | 1.00 | 2023-03-25 | 📦 mpc001/auto_avsr 📦 umbertocappellazzo/llama-avsr |
| 2 | DistillAV | Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models | 1.40 | 2025-02-09 | 📦 jxzhanggg/DistillAV |