Pinpoints what a musician played wrong against the reference score, then writes teacher-quality practice feedback grounded in retrieved music pedagogy.
-
Updated
Jul 1, 2026 - Python
Pinpoints what a musician played wrong against the reference score, then writes teacher-quality practice feedback grounded in retrieved music pedagogy.
An HCQT variant of BTC for musical chord recognition, plus a reproducible mir_eval benchmark. Honest result: it ties baseline BTC on held-out public data (GuitarSet, Schubert) — not better. Ships the model + weights, the benchmark harness, honest negative results, and a guide to extend the HCQT base to melody/bass/transcription.
Add a description, image, and links to the mir-eval topic page so that developers can more easily learn about it.
To associate your repository with the mir-eval topic, visit your repo's landing page and select "manage topics."