Show HN: I made an audio-to-MIDI model 60x more efficient
0 comments
- Points4
- Comments0
0 comments
I released dettato, my open weight audio to midi transcription model. It beats muscriptor 1.3b on every set and is roughly 60x smaller, without training on copyrighted recordings. Feel free to ask questions
Story details from Hacker News ↗ · linked article on kobi.music.
Show HN: I made an audio-to-MIDI model 60x more efficient was first seen on Hacker News · Show HN on Nov 17, 2026. Since then it has appeared in 35 checks on 2 different days. Its best position was #24 of 30, reached on Nov 17, 23:52 UTC. It dropped off the list after Nov 18, 00:52 UTC.
Position on Hacker News · Show HN at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hacker News.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 18, 00:52 UTC, after 2 days of trending.
#24 on Hacker News · Show HN, on Nov 17, 23:52 UTC. Trendoday checks this list every 30 minutes.
It was first seen on Nov 17, 2026 and has been on the list on 2 days (35 checks) since.
4 points and 0 comments; submitted by hidude562 on Nov 17, 2026.