search

lucidrains / audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MIT License
2.37k stars 255 forks source link

fix generate #70

Closed zhvng closed 1 year ago

zhvng commented 1 year ago

generate() in CoarseTransformerWrapper and FineTransformerWrapper only uses initial tokens. Pass in sampled tokens instead