search

SonyCSLParis / music2latent

Encode and decode audio samples to/from compressed latent representations!
Other
146 stars 7 forks source link

[Question] Can we reconstruct the original audio from the latent embeddings? #3

Open sleepingcat4 opened 2 months ago

sleepingcat4 commented 2 months ago

I wanted to use your project to create a dataset but if original audio can be reconstructed then I can't : ( That's why, I need to know before getting started. [I want to make latent for 20-30TB data]

marcoppasini commented 2 months ago

Yes, latents can be decoded back to waveforms (this is the main goal of Music2Latent, so you may explore other models in your case).

sleepingcat4 commented 2 months ago

@marcoppasini are you guys planning to make the original training code open source? If yes, then I may use your model for training and completely hide the source of my audio