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

Training dataset #264

Open hahust191806 opened 10 months ago

hahust191806 commented 10 months ago

Hi guys! I'm doing a music inpainting problem, my input is a vocal track, my task is to generate a music segment corresponding to that vocal, so my dataset includes 2 parts, 1 is vocal, 2 is instrument. So what will be the dataset for the Semantic, Coarse, Fine phase in the two vocal and instrumental episodes?