Reminds me of this project to generate every melody possible algorithmically in order to fight music copyright lawsuits. https://allthemusic.info/
Thanks. I enjoyed watching the TEDx talk on that page.
Show HN: I trained a 125M model to autocomplete piano on-device
101–110 of 135 posts
Re: Show HN: I trained a 125M model to autocomplete piano on-device
#102Hearing the start of Für Elise, and then it being taken in an incredibly different direction, is surprisingly disconcerting.
There's an incredibly funny bit (if you're into absurdist comedy) by Hans Teeuwen about the disconcerting direction a well known song can take: https://www.youtube.com/watch?v=FCDPxNyLAww
The disconcerting effect is enhanced by hearing the Dutch voice and reading the Dutch subtitles which don't quite match up with what he is saying in English! - until it all goes off into musical absurdity. Thanks for sharing.
Re: Show HN: I trained a 125M model to autocomplete piano on-device
#103This sort of “autocomplete” is actually fundamental to how classical composers were trained. For anyone interested, I’d highly recommend reading Robert Gjerdingen’s article Gebrauchs-Formulas. https://www.researchgate.net/publication/259731561_Gebrauchs... You can also listen to the transcript of four Russian composers, including Rachmaninoff, playing this pattern recognition and generation game at a dinner party in…
I'm a little lost. What am I listening for in that video?
Classical jamming.
Re: Show HN: I trained a 125M model to autocomplete piano on-device
#104[flagged]
Re: Show HN: I trained a 125M model to autocomplete piano on-device
#105I would love to see a jamming partner. So I could play along him on the same piece.
Re: Show HN: I trained a 125M model to autocomplete piano on-device
#106Classical pianist and software product designer here. I see so much in common with this project and the numerous AI-based UX design tools out there. Whether it's music or UI, now that the "generation" portion of the work costs zero, all that remains is taste. And so much of taste comes from exploring and killing off possibilities that turn out to be dead-ends. I love the idea that models like these will help us find…
[flagged]
Re: Show HN: I trained a 125M model to autocomplete piano on-device
#107Looks neat! I'd love for it to feed the MIDI notes back into my player piano instead of playing out of my iPhone's (comparatively tinny) speakers though.
Re: Show HN: I trained a 125M model to autocomplete piano on-device
#108[flagged]
>I guess no one actually wants to learn about harmony, about voicing, and voice leading, spend the hours. No one wants to learn how to actually play an instrument. I guess no one is willing to do the work. They want to just press some keys and declare that they made what the computer generated.
I don't understand that as a takeaway. Even if this worked perfectly, it would not be meaningfully stopping or discouraging anyone from learning music, and no one is claiming that what this models outputs is something the player played. It's a toy that someone made presumably because they like piano.
Re: Show HN: I trained a 125M model to autocomplete piano on-device
#109Interesting. I do feel letting a machine generating notes is taking the joy out of improvisation, is it not? I think one of the great, early, joys of learning a piano is gaining the following intuitions: The seemingly harder path of learning sheet is actually faster. Your mind _should_ learn to think in two dimensions Spatial — where fingers go — and Time — pitch and tempo – ** when learning. The _internalization_ of…
as with every discipline that AI and therefore computers can reason through suddenly: you could always do the discipline you liked before for self fulfillment purposes, and you can still do it for self fulfillment purposes now
But most people who want to get good at their main discipline, even for self-fulfillment purposes, have been gaining the necessary experience through their job, because an unrelated job takes away too much time to do so.
Re: Show HN: I trained a 125M model to autocomplete piano on-device
#110I 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
There is this in the post:
> The final dataset contained a few hundred thousand MIDI files, representing roughly 300 million note events.