search

lucidrains / audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MIT License
2.33k stars 249 forks source link

Bug? mask = True #164

Closed maitycyrus closed 1 year ago

maitycyrus commented 1 year ago

https://github.com/lucidrains/audiolm-pytorch/blob/e2579052a7ae9036b32aaf817e12f7f7be14ebf4/audiolm_pytorch/hubert_kmeans.py#L82

shouldn't mask be set to False since default value is True?

lucidrains commented 1 year ago

@maitycyrus i checked and yes indeed they have it turned on :cry: thank you for finding this issue!