List your company
ResearchFormerly WizWand

Visual Speech Recognition on LRS3 Low-Resource 30h labelled v1 (test)

0.024WERUSR
0.004240.137620.2710.40438Nov 4, 2024
Updated 8mo ago

Evaluation results

MethodLinks
USRPre-train data=LRS3+Vox2, Shared params=true, Model scale=Large2024.110.024
USRPre-train data=LRS3+Vox2, Shared params=true, Model scale=Base(+)2024.110.025
VATLMPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.027
AV-data2vecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.027
USRPre-train data=LRS3, Shared params=true, Model scale=Base(+)2024.110.03
AV-data2vecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.033
AV-HuBERTPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.033
VATLMPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.034
VATLMPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.036
BRAVEnPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.04
AV-HuBERTPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.04
AV-data2vecPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.042
AV-HuBERTPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.047
USRPre-train data=LRS3+Vox2, Shared params=true, Model scale=Large2024.110.269
USRPre-train data=LRS3+Vox2, Shared params=true, Model scale=Base(+)2024.110.284
AV-data2vecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.308
BRAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.308
Lip2VecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.312
VATLMPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.316
AV-HuBERTPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.325
RAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.110.325
BRAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.351
USRPre-train data=LRS3, Shared params=true, Model scale=Base(+)2024.110.36
AV-data2vecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.378
RAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.402
Lip2VecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.406
VATLMPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.426
BRAVEnPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.434
AV-data2vecPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.452
AV-HuBERTPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.110.461
RAVEnPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.47
VATLMPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.48
Lip2VecPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.495
AV-HuBERTPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.110.518