Automatic Speech Recognition on LRS3 Low-Resource 30h labelled v1 (test)
2.3WER (%)BRAVEn
Evaluation Results
| Method | Links | |
|---|---|---|
| BRAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.11 | 2.3 | |
| USRPre-train data=LRS3+Vox2, Shared params=true, Model scale=Large2024.11 | 2.4 | |
| USRPre-train data=LRS3+Vox2, Shared params=true, Model scale=Base(+)2024.11 | 2.6 | |
| RAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.11 | 2.7 | |
| AV-data2vecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.11 | 2.7 | |
| AV-HuBERTPre-train data=LRS3+Vox2, Shared params=false, Model scale=Large2024.11 | 2.9 | |
| BRAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.11 | 3 | |
| USRPre-train data=LRS3, Shared params=true, Model scale=Base(+)2024.11 | 3.2 | |
| AV-data2vecPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.11 | 3.7 | |
| RAVEnPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.11 | 3.8 | |
| BRAVEnPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.11 | 4 | |
| AV-data2vecPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.11 | 4.4 | |
| AV-HuBERTPre-train data=LRS3+Vox2, Shared params=false, Model scale=Base(+)2024.11 | 4.6 | |
| RAVEnPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.11 | 4.7 | |
| AV-HuBERTPre-train data=LRS3, Shared params=false, Model scale=Base(+)2024.11 | 4.9 |