Bugfix - Fixing validation dataset variable on FineTransformerTrainer

lucidrains / audiolm-pytorch

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

MIT License

2.45k stars 266 forks source link

Closed rgxb2807 closed 1 year ago

rgxb2807 commented 1 year ago

Bugfix addressing #242

valid_dataset should set self.valid_ds to remain consistent with the code, otherwise an error is thrown that self.valid_ds doesn't exist.

lucidrains commented 1 year ago

thanks Ryan!