Fix off-by-one error in train step update

lucidrains / audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

MIT License

2.39k stars 255 forks source link

Closed LWprogramming closed 1 year ago

LWprogramming commented 1 year ago

OK now the fix should work, having tested it all merged into one branch