lucidrains / audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MIT License
2.32k stars 249 forks source link

bugfix - swap codec variable for course wrapper #248

Closed rgxb2807 closed 8 months ago

rgxb2807 commented 8 months ago

quick bugfix responding to #246

changing encodec to self.codec

With this change, you can set return_coarse_generated_wave=True and return just the wave generated by the coarse transformer.

lucidrains commented 8 months ago

yes thanks!