List your company
ResearchFormerly WizWand

Automatic Speech Recognition on LRS3 High-Resource 433h labelled v1 (test)

0.012WERBRAVEn
0.011280.016140.0210.02586Nov 4, 2024
Updated 8mo ago

Evaluation results

MethodLinks
BRAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.012
USRPre-train data=LRS3+Vox2, Shared params=true, Model scale=Large2024.110.012
AV-HuBERTPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.013
AV-data2vecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.013
BRAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.014
RAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.014
u-HuBERTPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.015
USRPre-train data=LRS3+Vox2, Shared params=true, Model scale=Base(+)2024.110.016
AV-data2vecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.017
BRAVEnPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.019
USRPre-train data=LRS3, Shared params=true, Model scale=Base(+)2024.110.019
RAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.019
AV-data2vecPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.02
AV-HuBERTPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.02
RAVEnPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.022
AV-HuBERTPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.03