mlecardonnel/drumsheet

How mlecardonnel/drumsheet works

DrumSheet is a command-line drum-audio transcription tool. The user supplies audio; the CLI loads four classifiers and delegates transcription to DrumAudio, which detects percussion events, classifies their spectrograms, and produces a LilyPond score before invoking LilyPond to render a PDF. The README also describes the MedleyDB-based training context and the four instrument-specific classifiers. The source excerpts support the runtime flow; model internals and dataset processing are not shown.

Main entry points: main.py Transcription CLI · drum_audio.py Spectrogram classification · CY_60epochs Cymbal model · HH_ResNet Hi-hat model

Components 13

Command entry

Transcription CLI src/main.py

Audio transcription

DrumAudio src/drum_audio.py
Percussion detection src/drum_audio.py
Spectrogram classification src/drum_audio.py

Instrument classifiers

Cymbal model models/CY_60epochs
Hi-hat model models/HH_ResNet
Kick model models/KD_ResNet
Snare model models/SD_ResNet

Score output

LilyPond score generation src/drum_audio.py
LilyPond score file data/lilypond_files/MusicDelta_80sRock_Drum.ly
PDF score data/pdf_files/MusicDelta_80sRock_Drum.pdf

Other components

Audio provider
LilyPond renderer

Connections 16

Audio provider → Transcription CLI: provides audio src/main.py
Transcription CLI → DrumAudio: constructs src/main.py
Transcription CLI → Cymbal model: loads model src/main.py
Transcription CLI → Hi-hat model: loads model src/main.py
Transcription CLI → Kick model: loads model src/main.py
Transcription CLI → Snare model: loads model src/main.py
DrumAudio → Percussion detection: detects events src/drum_audio.py
DrumAudio → Spectrogram classification: classifies events src/drum_audio.py
Spectrogram classification → Cymbal model: predicts cymbals src/drum_audio.py
Spectrogram classification → Hi-hat model: predicts hi-hats src/drum_audio.py
Spectrogram classification → Kick model: predicts kicks src/drum_audio.py
Spectrogram classification → Snare model: predicts snares src/drum_audio.py
Transcription CLI → LilyPond score generation: requests score src/main.py
LilyPond score generation → LilyPond score file: writes score src/drum_audio.py
Transcription CLI → LilyPond renderer: requests rendering src/main.py
LilyPond renderer → PDF score: renders PDF

Drawn by GitDiagram on November 9, 2026 from the repository's file tree, README and source files. Read as Markdown ·