choijeongsoo/av2av
[CVPR 2024] AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation
PythonMIT
Issues
- 1
- 3
- 1
Vocoder training code
#5 opened by ilucasgoncalves - 1
Unit2Lip training - sync loss
#4 opened by roudimit - 2
Training code
#3 opened by roudimit - 2
License?
#2 opened by mtresearcher - 1
typo in requirements.txt ?
#1 opened by suruoxi