Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Audio-Visual Automatic Speech Recognition on VisSpeech zero-shot
Loading...
16.6
WER
AVFormer
14.6508
27.8079
40.965
54.1221
Mar 29, 2023
WER
Updated 4d ago
Evaluation Results
Method
Method
Links
WER
AVFormer
Modality=A+V, LibriSpe...
2023.03
16.6
BEST-RQ
Modality=A, LibriSpeec...
2023.03
16.69
BEST-RQ
Modality=A, LibriSpeec...
2023.03
28.62
AVATAR
Modality=A+V, LibriSpe...
2023.03
35.59
AVATAR
Modality=A+V, LibriSpe...
2023.03
35.66
AVATAR
Modality=A, LibriSpeec...
2023.03
65.33
Feedback
Search any
task
Search any
task