nintoracaudio

Thanks for the feedback!

1. For sure, I was thinking something along the lines of a multiview VAE that gets as input either `f(z|audio, midi)` or `f(z|dx7_parameters)` and must produce as output `f(audio|midi,z)` or `f(dx7_parameters|z)`

2. Yea, I have tried to pick apart Ableton files in the past but the format is a bit of a nightmare, it might be easier to use source separation like https://github.com/deezer/spleeter to build your dataset!

For (2), yea definitely threw this all together a little too quickly. I have updated the README in https://github.com/Nintorac/NeuralDX7 to give a little explanation of the specific code used for this site.

Hope that helps and feel free to get in contact [email protected] or create an issue if I can help to make anything clearer