jyangliu issues

Repositories
Issues
Comments

Results 2 issues of


                                            jyangliu

Token Alignment in Wav2Vec2.0

Can pretrained Wav2Vec2.0 model facebook/wav2vec2-base-960h ensure alignment between input and output token? I find that facebook/wav2vec2-base-960h has been finetune with CTC.

How to get whole face parsing network structure

I'm trying to get the feature maps of face parsing network. Now, jit load is using, so I can not kown the network structure. How can I get the feature...