📊 Showing 4 results | 📏 Metric: Word Error Rate (WER)
| Rank | Model | Paper | Word Error Rate (WER) | Date | Code |
|---|---|---|---|---|---|
| 1 | RAVEn Large 📚 | Jointly Learning Visual and Auditory Speech Representations from Raw Data | 1.40 | 2022-12-12 | 📦 ahaliassos/raven |
| 2 | AV-HuBERT Large 📚 | Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction | 1.30 | 2022-01-05 | 📦 facebookresearch/av_hubert 📦 guxm2021/MM_ALT |
| 3 | Llama-AVSR 📚 | Large Language Models are Strong Audio-Visual Speech Recognition Learners | 0.81 | 2024-09-18 | 📦 umbertocappellazzo/llama-avsr |
| 4 | Whisper 📚 | Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation | 0.68 | 2024-06-14 | 📦 roudimit/whisper-flamingo |