# azuwis/pianotrans

Simple GUI for ByteDance's Piano Transcription with Pedals

Repository: https://github.com/azuwis/pianotrans
Canonical: https://ross.abutalabs.com/products/pianotrans
Language: Nix
License Family: other
Topics: piano, transcription, ai
Last push: 2026-08-26T10:26:38+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 8, longevity 100
- inputs: {"age_days": 2038, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1509, forks 147 (observed 2026-08-28T04:04:55.676046+00:00)

## What it is
A simple GUI wrapper and packaging for ByteDance's Piano Transcription with Pedals, a PyTorch system that converts piano audio recordings into MIDI files including pedal events. It ships prebuilt Windows binaries and Nix packages for Linux and macOS, with optional CLI usage.

## Use cases
- convert piano recordings to midi files
- transcribe piano audio with sustain pedal
- batch transcribe audio or video files to midi
- extract midi from a piano performance recording
- run piano transcription locally with gpu acceleration

## When to choose
- you want a ready-to-run desktop app for piano-to-MIDI transcription on Windows, Linux, or macOS
- you use Nix and want a reproducible install of ByteDance's piano transcription model
- you need pedal (sustain) information included in the transcribed MIDI

## When to avoid
- you need transcription of instruments other than piano
- you want a headless server or library API rather than a desktop GUI
- your machine has less than 4GB RAM or no room for the large model download

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, audio-processing, gui, cli
- domain: machine-learning, media, cross-platform
- platform: windows
- tags: piano-transcription, midi, pytorch, nix-packaging, music, audio, linux, macos, desktop

## Member repositories
- azuwis/pianotrans (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:55.676046+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:29.018837+00:00, confidence not recorded.
  - readme: https://github.com/azuwis/pianotrans (fetched 2026-08-28T04:04:55.676046+00:00, sha 40900d527d8d)
- Data as of 2026-08-30T08:39:29.467469+00:00.