Gallery
About
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.
Comments (3)
125M params hitting 108 notes/sec on mobile hardware is wild
what dataset did u use for the piano training
market for piano autocomplete seems pretty niche tbh
Related Products
CAVN AI | AI Music Generator
CAVN AI is an innovative platform that allows users to generate music
Typist
Transcribe audio to text in seconds.
rapym
TKCORE AI
All-in-one AI platform featuring TkCore-V5.5-Pro & top LLMs
Textsight.ai
TextSight.ai detects AI-like writing, gives a 0–100 Authenticity / Humanization
ai image prompts
Copy-paste AI image prompts that actually work.
ComingUp