search

lucidrains / audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MIT License
2.36k stars 255 forks source link

set log_losses_every doesn't work #134

Closed yygle closed 1 year ago

yygle commented 1 year ago

https://github.com/lucidrains/audiolm-pytorch/blob/main/audiolm_pytorch/trainer.py#L344 It seems the not here should be removed?