jukebox VS tt-vae-gan

openai/jukebox: Music Generation

https://github.com/openai/jukebox The demo code is there.

I didn't even know about it until I heard Sam Altman casually mention it in an interview, I was expecting some basic tunes generator, but this is so amazing! I mean yeah the voices are not clear, it's muffled, but look at how far have image models progressed, if you applied the same amount of collaborative effort here, the results could be amazing! ElevenLabs showed how good and clear can AI-created voices sound. The only reason I can think of is that the Jukebox code is under view license only.

OpenAI had this figured out 3 years ago: https://openai.com/blog/jukebox/ . You could then even define your own text. Model is open source too.

They've had jukebox for a few years now, so I'm sure some new model will get released and explode overnight, like what chatGPT did.

That already exists

This model is designed to output raw audio.

However, there are many models which do output midi. That's actually much simpler, and has been done already a few years ago.

I thought OpenAI did this. But then, I might misremember, because their Jukebox actually also seems to produce raw audio (https://openai.com/blog/jukebox/).

However, midi generation is so easy, you even find it in some tutorials: https://www.tensorflow.org/tutorials/audio/music_generation

Link for demonstration, code, and tutorial: https://github.com/RussellSB/tt-vae-gan

I've been working on an open source implementation for the past month. The link for it can be found here. But have since been struggling with a load of mode collapse - or the model outputting "blurry" spectrograms not quite capturing the same initial structure as they should.