Moisés Horta Valenzuela
Moisés Horta Valenzuela
@branlsnyder Yes, indeed I've been experimenting with that approach; recording each individual latent dimension into audio, from the output of either the prior or the encoder model and it seems...
It seems you need to finish training until the second phase of training, which by default kicks in after 1 Million steps, or you can set it custom with the...
@chebmarcel The prior is actually another neural network, a type of RNN, which basically tries to predict the most likely next latent variable of your pre-trained RAVE model...it is needed...
@chebmarcel depends on you, I usually train beyond 1M steps for the prior, but really depends on your dataset and how it converges
@gyuchulm Yes, this is all trained on the default setup for v2. I also experienced the same, it did not work when exporting and running on nn~ even tho I...
As I mentioned, your implementation seems a bit more clear to me than Simo's. Although I will give his a try as well :)
yeah, that would be great. I'm currently trying to scale up your implementation but I seem to be either very quickly overfitting or just NaN/Inf gradients while training on a...
Yes, definitely. On some occasions there is overfitting, tried mitigating with dropout. On some occasions the divergence has been mitigated with lower LR. Any other advice is greatly appreciated! Looking...
Bumping this up, hoping it gets implemented soon 👍
Great! This would be amazing for Pd external as well.