sony/DiffRoll

PyTorch implementation of DiffRoll, a diffusion-based generative automatic music transcription (AMT) model

39
/ 100
Emerging

This project helps musicians, music producers, and researchers automatically convert audio recordings of piano music into a 'piano roll' format, which visually represents notes over time. You input an audio file of piano music, and it outputs a detailed piano roll that shows which notes were played, when, and for how long. This is ideal for anyone who needs to quickly get a structured, editable representation of a piano performance from an audio source.

No commits in the last 6 months.

Use this if you need to accurately convert piano audio recordings into a digital piano roll for editing, analysis, or further music production.

Not ideal if you need to transcribe music from instruments other than piano or require real-time transcription, as this is for batch processing pre-recorded audio.

music-transcription piano-performance audio-analysis music-production score-creation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

80

Forks

11

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sony/DiffRoll"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.