Speech-Backbones icon indicating copy to clipboard operation
Speech-Backbones copied to clipboard

Possibly missing __dict__ in the Projector class' constructor

Open Sri-Harsha opened this issue 2 years ago • 0 comments

While loading the pretrained weights of the ST2VecEncoder, I had to replace **conv_cfg_i with **conv_cfg_i.__dict__ in __init__ of the Projector class (SPIRAL/nemo/collections/asr/parts/spec2vec.py). Doing this allowed me to load all the weights and match the keys successfully -- nonetheless, i was curious to know if I was missing any installation?

Sri-Harsha avatar Jul 05 '22 04:07 Sri-Harsha