HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Automatic Speech Recognition On Lrs2

Metrics

Test WER

Results

Performance results of various models on this benchmark

Paper Title
TM-CTC10.1Deep Audio-Visual Speech Recognition
TM-seq2seq9.7Deep Audio-Visual Speech Recognition
CTC/attention8.2Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture
LF-MMI TDNN6.7Audio-visual Recognition of Overlapped speech for the LRS2 dataset
Whisper-LLaMA6.6Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition
End2end Conformer3.9End-to-end Audio-visual Speech Recognition with Conformers
MoCo + wav2vec (w/o extLM)2.7Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition
CTC/Attention1.5Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels
Whisper1.3Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
0 of 9 row(s) selected.
Automatic Speech Recognition On Lrs2 | SOTA | HyperAI