Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I trained a 125M model to autocomplete piano on-device

simedw.com

Post reply on HN
Print view View original

1–10 of 135 posts

Show HN: I trained a 125M model to autocomplete piano on-device

#1

Post by simedw »

I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15).

The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device.

The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

Show HN: I trained a 125M model to autocomplete piano on-device
simedw.com

Re: Show HN: I trained a 125M model to autocomplete piano on-device

#5

Post by kennyadam »

qmmmur wrote: post #3

[flagged]

Is this HN? Aren't people supposed to tinker with tech for no reason other than seeing if they can? Is everything that involves a transformer now just AI BAD? Is that what the world has devolved into? Each side screaming "Orange Man Bad" and endless variations at each other?

Re: Show HN: I trained a 125M model to autocomplete piano on-device

#6

Post by simedw »

evalystai wrote: post #4

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.

Re: Show HN: I trained a 125M model to autocomplete piano on-device

#8

Post by tescreal »

kennyadam wrote: post #5
qmmmur wrote: post #3

[flagged]

Is this HN? Aren't people supposed to tinker with tech for no reason other than seeing if they can? Is everything that involves a transformer now just AI BAD? Is that what the world has devolved into? Each side screaming "Orange Man Bad" and endless variations at each other?

While it is a neat parlor trick, a lot of people have specific grevience against the application to art. AI has only served to further disempower artists broadly, and arguably it pushes "art" to a lower common denominator. Try to actually situate yourself in "why" people get rankled instead of making it a thought terminating cliche.

Re: Show HN: I trained a 125M model to autocomplete piano on-device

#9

Post by meerita »

kennyadam wrote: post #5
qmmmur wrote: post #3

[flagged]

Is this HN? Aren't people supposed to tinker with tech for no reason other than seeing if they can? Is everything that involves a transformer now just AI BAD? Is that what the world has devolved into? Each side screaming "Orange Man Bad" and endless variations at each other?

It is tiring to read these people. It feels like nothing will please them, but their own ideas, work, methods.

Re: Show HN: I trained a 125M model to autocomplete piano on-device

#10

Post by Razengan »

qmmmur wrote: post #3

[flagged]

  What is the goal here?
To eventually prove that Intelligence™ and Creativity™ isn't special?

Or maybe there is some other "spark" deeper within?

When everyone can make anything as soon as they think of it, what will set us apart?

Post reply on HN