search

lucidrains / audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MIT License
2.36k stars 255 forks source link

sampling rate of audio when using Encodec #148

Open zhouyong64 opened 1 year ago

zhouyong64 commented 1 year ago

For using Encodec, current code only supports 24KHz audios. So when training CoarseTransformer and FineTransformer, the input wave data also need to be 24KHz?

lucidrains commented 1 year ago

@zhouyong64 yup, that is correct, but should also be automatically taken care of (example)