How is this possible? I thought deep learning models struggle with approximating periodic functions like sin.
Here is the MusicGen paper from Facebook research: https://arxiv.org/abs/2306.05284 MusicGen is an LLM on top of EnCodec tokens, instead of working directly with audio. EnCodec is neural audio compression algorithm that encodes audio as tokens from a codebook. It's a really clever trick!
MusicGen-Looper: Generate fixed-bpm loops from text prompts
11–20 of 25 posts
Re: MusicGen-Looper: Generate fixed-bpm loops from text prompts
#12Re: MusicGen-Looper: Generate fixed-bpm loops from text prompts
#13"You must sign in to run this model" In this day and age, curiosity is not worth the risk.
Re: MusicGen-Looper: Generate fixed-bpm loops from text prompts
#14It worked better with "suomisaundi psychedelic trance spugedelic".
This is a neat idea in many ways.
Re: MusicGen-Looper: Generate fixed-bpm loops from text prompts
#15Re: MusicGen-Looper: Generate fixed-bpm loops from text prompts
#16That thing refused to make me a 160 bpm chicago acid house loop... what a severe lack of imagination :-P
I think you just described chicago acid house :-P
Re: MusicGen-Looper: Generate fixed-bpm loops from text prompts
#17Edit: am i mis-interpreting the term looper here? it just made an output with a fade out.
Re: MusicGen-Looper: Generate fixed-bpm loops from text prompts
#18Re: MusicGen-Looper: Generate fixed-bpm loops from text prompts
#19File "predict.py", line 211, in predict raise ValueError( ValueError: Failed to generate a loop in the requested 60.23 bpm. Please try again.
EDIT: At 52 bpm (exact) it seems to work. What it generated would not sound good if looped however. In terms of style.. it sounded a little music box like - celesta or so (think of the beginning of the Harry Potter soundtrack) with some sustained strings and pizzicato strings. That would be appropriate, except the rhythm and chords are fairly random and I wouldn't exactly call this musical :)