Audiolm as an embedder model?

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

Audiolm as an embedder model? #271

Open Darel13712 opened 4 months ago

Darel13712 commented 4 months ago

Hey, I would like to know if it is possible to use this model to get a dense embedding for an audio file to use in downstream tasks without training the whole model. How could I do that?