Speech Recognition On Lrs3 Ted

Word Error Rate (WER)

Results

Performance results of various models on this benchmark

		Paper Title
RAVEn Large	1.4	Jointly Learning Visual and Auditory Speech Representations from Raw Data
AV-HuBERT Large	1.3	Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction
Llama-AVSR	0.81	Large Language Models are Strong Audio-Visual Speech Recognition Learners
Whisper	0.68	Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation

0 of 4 row(s) selected.