List your company

Lip Reading on LRS3 (test)

17WERViT-3D
15.02428.36241.755.038Jun 10, 2023Oct 17, 2023Feb 23, 2024Jul 2, 2024Nov 8, 2024Mar 17, 2025Jul 25, 2025

Evaluation results

MethodLinks
ViT-3DPhoneme-based=false, Input=Video, Extra Data=true, Total Hours=900002025.0717
V-ASRPhoneme-based=true, Input=Video, LLM=NLLB(1.3B), Extra Data=false, Total Hours=4382025.0717.3
VALLRPhoneme-based=true, Input=Video, LLM=LLaMA, Extra Data=false, Total Hours=302025.0718.7
Auto-AVSRPhoneme-based=false, Input=Video, Extra Data=true, Total Hours=34482025.0719.1
PV-ASRPhoneme-based=true, Input=Video+117-Points, LLM=NLLB(1.3B), Extra Data=false, Total Hours=4382025.0720.3
AV-ViTMode=Full-Shot, Labeled Utts Video(hrs)=90000, Publicly Available Dataset=false2023.0625.9
OpenSRMode=Full-Shot, Unlabeled Utts=LRS3+VC2-EN, Labeled Utts Video(hrs)=4332023.0628.5
AV-HubertMode=Full-Shot, Unlabeled Utts=LRS3+VC2-EN, Labeled Utts Video(hrs)=4332023.0628.6
OpenSRMode=Zero-Shot, Unlabeled Utts=LRS3+VC2-EN2023.0630.6
SubMode=Full-Shot, Labeled Utts Video(hrs)=2676, Publicly Available Dataset=false2023.0630.7
VTPPhoneme-based=false, Input=Video, Extra Data=true, Total Hours=26762025.0730.7
VisualSRMode=Full-Shot, Labeled Utts Video(hrs)=14592023.0631.5
Auto-AVSRPhoneme-based=false, Input=Video, Extra Data=true, Total Hours=8182025.0733
RecurrentNNMode=Full-Shot, Labeled Utts Video(hrs)=31000, Publicly Available Dataset=false2023.0633.6
CM-auxPhoneme-based=false, Input=Video, Extra Data=false, Total Hours=4382025.0736.3
VTPPhoneme-based=false, Input=Video, Extra Data=true, Total Hours=6982025.0740.6
LiraMode=Full-Shot, Labeled Utts Video(hrs)=5902023.0643.3
Hyb.-Conf.Phoneme-based=false, Input=Video, Extra Data=true, Total Hours=5902025.0743.3
ASSTGCNPhoneme-based=false, Input=Video+38-Points, Extra Data=false, Total Hours=4382025.0762.7
P-ASRPhoneme-based=true, Input=117-Points, LLM=NLLB(1.3B), Extra Data=false, Total Hours=4382025.0766.4