Variational autoencoder for time series denoising and dimentionality reduction

I have a dataset X of multiple series say 100 (size=100). I would like to use VAE to both denoise the data and reduce the dimensions to a smaller latent space Z (size Z size X), because I will use this smaller latent set afterwards as an input for a NN regression problem.

It's the same procedure used when we use PCA or factor analysis in order to obtain a noiseless condesate rappresentation (especially when variables share information) except that I do not want to impose any transformation and I let the VAE to provide me with the best one.

Does anybody know a good reference with code for this? (better pytorch, but keras is fine too)

I know the theory so I just need some guide on the code side