pytorch/audio

How to train a real-time av-asr pretrain model

Zhaninh opened this issue ยท 0 comments

๐Ÿš€ The feature

There is an example for hubert training here, but has no example about real-time av-asr for other languages.

Motivation, pitch

I'm woking on lipreading without a pretrained model to continue train the pretrained model like real-time av-asr.

Alternatives

No response

Additional context

No response