Hi @csf123123, we are not allowed to provide the corresponding pretrained model for avsr repository due to legal issues. The model you've linked is seperated from the repository. Please note that that model is compatible with torchaudio version 2.0.2.
Hi , Thanks for sharing your work. May I ask when will the real-time audiovisual pretrained models be likely to be released? I download a realtime avsr model from https://download.pytorch.org/torchaudio/tutorial-assets/device_avsr_model.pt . Then I want to test the eval.py(https://github.com/pytorch/audio/tree/main/examples/avsr/eval.py ). But it was wrong when load the model