I think this is a great project and very HN. Not sure why the comments are so focused on the deliverable- you learned way more and had a much more interesting experience.
One think I didn't see mentioned in the post- maybe I missed it- how large was the data? How many samples did you use to pretrain and post-train
Oh, a cool idea! I just tried it, works pretty well. Kudos!
One feature request:
Instead of playing the AI-generated audio solely through the iPhone's speakers, add an option to send the audio as midi notes to a device (probably the same one you received the mini notes from).
Ah, MIDI files. The only type of music you could realistically download from the internet back in the day, and you had to wake up at ungodly hours so that your dialup modem would not rack up a massive phone bill.
I would love something like that, except that I play the melody, and it produces proper 3-4 part accompaniment, preferably in good baroque style. Extra bonus if it could also write it into a file in a format suitable for music editing programs.
This feels like a natural next step. Starting with a simple melody and having the system fill in the rest while still following your playing style could make it much more useful for experimentation than generating a complete piece from scratch.
An early attempt at this was Microsoft Songsmith [1] all the way back in 2009, which would take a melody (usually recorded by mic) and try to scaffold an accompaniment around it though obviously not realtime in any sense of the word.
The closest we've had to realtime orchestration around a melody in the "real world" is probably arranger keyboards though your left hand is still responsible for the chord progression itself.
The biggest speed improvement came from changing the note representation when I switched to compound note events: roughly 5× fewer autoregressive passes per note.
For the current model I’m using Core ML, which optimizes the kernels the first time you run it. I haven’t actually spent that much time tuning performance beyond that.
The answer about changing the note representation was interesting. Sometimes a change in how the problem is represented ends up giving a much bigger improvement than trying to optimize the model itself.
This is really fun. Scaler 3 starts with a chord progression and lets you break it down into musical performances and parts. Useful for ideation when producing.
Would be fun to get a midi clock going and play some chords on my piano and have my synth start jamming along with the bass and my keyboard doing some performance. Or any combination of the above.
That would be a really interesting direction. At that point it starts feeling less like autocomplete and more like having another musician reacting to what you're playing in real time.
How would you expand this to support elements like attack ("velocity of the key-down" in piano speak), grace notes, timing etc. Would each of those be part of this model or another model? How would you model an arbitrary element (pedal, duration, etc...)
The idea is awesome! :) However there's definitely much room for improvement, first of all rythm and composition (so there's some sense of musical form).
Yes, I think I’ve gotten it to roughly a GPT-2 level: good enough to share, but with a lot of room left to improve. I think adding some kind of bar/measure token might help with rhythm, and perhaps some form of longer-term planning for the overall composition.
This is so amazing, can you improve the quality of generation at the cost of notes per seconds ? No one can play 108 notes/sec anyways, maybe you can train the model to do CoT for better quality
Yes, some kind of planning step is on my TODO list. Another thing I want to try is generating a few continuations in parallel, picking the one that looks best, and then continuing from there. Maybe the picking could be automatic.
I can probably squeeze out quite a bit more than 100 notes/sec as well. I haven’t spent much time optimizing inference yet.
Reminds me of this project to generate every melody possible algorithmically in order to fight music copyright lawsuits. https://allthemusic.info/
I think this is a great project and very HN. Not sure why the comments are so focused on the deliverable- you learned way more and had a much more interesting experience.
One think I didn't see mentioned in the post- maybe I missed it- how large was the data? How many samples did you use to pretrain and post-train
Oh, a cool idea! I just tried it, works pretty well. Kudos!
One feature request:
Instead of playing the AI-generated audio solely through the iPhone's speakers, add an option to send the audio as midi notes to a device (probably the same one you received the mini notes from).
Reminds me of Francois Pachet’s Continuator (all the way back in 2003, using hierarchical markov models)
https://www.francoispachet.fr/continuator/
Ah, MIDI files. The only type of music you could realistically download from the internet back in the day, and you had to wake up at ungodly hours so that your dialup modem would not rack up a massive phone bill.
MIDI is still widely used for professional music production. It sounded goofy back in the day because synthesizer it was played on was not very good.
I'm thinking canyon.mid on Microsoft GS Wavetable Synth.
I remember downloading MOD files. It was just a bit larger than midi, but sounded better. I had a PC but I think it was an Amiga thing
I would love something like that, except that I play the melody, and it produces proper 3-4 part accompaniment, preferably in good baroque style. Extra bonus if it could also write it into a file in a format suitable for music editing programs.
This feels like a natural next step. Starting with a simple melody and having the system fill in the rest while still following your playing style could make it much more useful for experimentation than generating a complete piece from scratch.
An early attempt at this was Microsoft Songsmith [1] all the way back in 2009, which would take a melody (usually recorded by mic) and try to scaffold an accompaniment around it though obviously not realtime in any sense of the word.
The closest we've had to realtime orchestration around a melody in the "real world" is probably arranger keyboards though your left hand is still responsible for the chord progression itself.
[1] - https://en.wikipedia.org/wiki/Microsoft_Research_Songsmith
That's a fun idea. You could start playing the piano and it kicks in with a base and drums for a jazz band.
Running a 125M model on-device at that speed is impressive. How much did you have to optimize the model to get that performance on an iPhone?
The biggest speed improvement came from changing the note representation when I switched to compound note events: roughly 5× fewer autoregressive passes per note.
For the current model I’m using Core ML, which optimizes the kernels the first time you run it. I haven’t actually spent that much time tuning performance beyond that.
The answer about changing the note representation was interesting. Sometimes a change in how the problem is represented ends up giving a much bigger improvement than trying to optimize the model itself.
This is really fun. Scaler 3 starts with a chord progression and lets you break it down into musical performances and parts. Useful for ideation when producing.
Would be fun to get a midi clock going and play some chords on my piano and have my synth start jamming along with the bass and my keyboard doing some performance. Or any combination of the above.
That would be a really interesting direction. At that point it starts feeling less like autocomplete and more like having another musician reacting to what you're playing in real time.
+1 all of this. That would be incredible (this already seems very cool - excited to get home and try it!)
How would you expand this to support elements like attack ("velocity of the key-down" in piano speak), grace notes, timing etc. Would each of those be part of this model or another model? How would you model an arbitrary element (pedal, duration, etc...)
Talking about AI music with some live human MIDI inputs, Magenta Realtime 2 was released a few weeks ago and is pretty fun.
https://magenta.withgoogle.com/magenta-realtime-2
The idea is awesome! :) However there's definitely much room for improvement, first of all rythm and composition (so there's some sense of musical form).
Thank you.
Yes, I think I’ve gotten it to roughly a GPT-2 level: good enough to share, but with a lot of room left to improve. I think adding some kind of bar/measure token might help with rhythm, and perhaps some form of longer-term planning for the overall composition.
This is so amazing, can you improve the quality of generation at the cost of notes per seconds ? No one can play 108 notes/sec anyways, maybe you can train the model to do CoT for better quality
Yes, some kind of planning step is on my TODO list. Another thing I want to try is generating a few continuations in parallel, picking the one that looks best, and then continuing from there. Maybe the picking could be automatic.
I can probably squeeze out quite a bit more than 100 notes/sec as well. I haven’t spent much time optimizing inference yet.
Amazing idea! Gonna hook this up to my little synthesizer and blast some square wave arpeggiated ML music!
I don’t have MIDI. How about whistling or playing the piano via microphone? Sounds easy. Another 6 month rabbit hole? :)
Even after a few years deep into AI, I find your application absolutely magic. This is very inspiring, thank you for sharing.
Cool work. I tried using LLMs to parse sheet music and they are really bad.
really incredible work! great use case, impeccable learning strategy, congrats!
Very cool! Can you say a little bit about the size of the DPO training examples and how long training took?
For DPO I only had around 700 preference examples, so not much data at all. That took about 12 minutes to train on a single GPU.
Pretraining was obviously a a lot slower, the 125M model took roughly half a day.
Gemma 4 E2B was too heavy for your needs?
This is really awesome thanks for sharing
> Eventually I used Gemini 3.5 Flash for pairwise evaluation
But, but… wouldn't that be… (gasp) DISTILLATION?
Fun project!