Dettato - Audio-to-MIDI transcription model 60x more efficient
Show HN: I made an audio-to-MIDI model 60x more efficient

Dettato is an open-source audio-to-MIDI transcription model from kobimusic that achieves state-of-the-art results with just 20M parameters — roughly 65x smaller than MuScriptor 1.3B. It outperforms MuScriptor and edges past Mirelo A2M v1.1 Pro on published benchmarks, all while being trained on zero copyrighted recordings using synthetic instruments, CC solo instruments from the URMP dataset, and ~20 soundfonts. Outputs are free for commercial use. Upload your own audio or try the demos to get performance MIDI with beat alignment.
The constraint of not using copyrighted recordings doesn't hold you back, but actually encourages innovation, and it's likely you'll end up with a better model in the end.
- jsphweid
I've been out of the loop since Magenta's MT3 model. This feels a lot better and significantly smaller. Very impressive, dude. And thank you!
- peaseagee
Congrats on training on open and public domain recordings. Thanks for proving this kind of work can be done in a more ethical way.
- oever
Audio-to-MIDI sounds very ambitious. How do you verify that the midi fits the audio? Does it result in useful beat detection? E.g. I'd very much like to have a way to map audio offset in a recording to labels in sheet music. But even beat detection in fairly standard jazz recordings fails often.
Does the model know when a piece (whole piece, not a section) is 3/4 or 4/4 th and can it give the onsets of all measures? Or all the midi notes just based on time and not organized rhythmically?