Tools, learning & writingFebruary 2026 onward

Interactive Tools, Learning & Writing

Piano video to MIDI

A web pipeline converting YouTube/Bilibili piano audio into editable MIDI, with optional timing/dynamics cleanup and a saved library.

PythonFlaskTranskunMIDIPyTorchpretty-midiyt-dlp
Why it sits here. Distinct creative integration with good candidate attribution and an understandable end-to-end function.
07 / A pitch. A piano roll. A new perspective.STUDY IN SPACE

THE QUESTION

How much useful cleanup belongs after transcription?

Turn a YouTube or Bilibili piano video into a downloadable MIDI file and an organized conversion library.

A LITTLE LESS BETWEEN YOU & THE NOTES
transcribe → clean up → MIDIoriginal timing
Concept diagram · not performance data

01 / IMPLEMENTATION & CONTRIBUTION

What the work involves

Donald built video ingestion, job orchestration, library deduplication, and MIDI postprocessing around upstream Transkun transcription.

Technical depth

Downloaded audio, model failures, GPU availability, overlapping notes, and variable timing need a coherent conversion flow.

Data and assumptions

User-supplied video/audio, predicted MIDI, estimated tempo, timing and velocity values. No private library or copyrighted recording is republished.

Audio transcription is provided by Transkun. The project does not claim a new transcription model.

The project family

pianovision_midi_converter

02 / THE EXPERIMENTAL RECORD

What the experiment taught

CUDA transcription can fail; the implementation retries on CPU. Musical transcription accuracy has not been independently evaluated.

What changed

Postprocessing adds partial sixteenth-note quantization, velocity smoothing, and same-pitch overlap trimming.

03 / RESULTS

What came out of it

A conversion workflow with serial queueing, CPU fallback after CUDA failure, optional timing and velocity cleanup, overlap trimming, and a saved MIDI library.

The lesson in the work

The useful product includes the handling around the model: input, recovery, cleanup, and retrieval.

04 / SUPPORTING EVIDENCE

Follow the source

Implementation notes, project records, and supporting artifacts.

Source context & project scope

Transkun is upstream, not a model Donald trained.

No hand-splitting implementation found.

The project does not establish that Donald plays piano or owns PianoVision.

User library/audio files were not inspected.

Transcription accuracy remains unmeasured.

Integration and product engineering; Transkun is an upstream dependency. The project is not evidence of Donald’s musical biography.

MIDI processing estimates tempo, moves timing 80% toward a sixteenth-note grid, smooths velocity, and trims same-pitch overlaps.

SOURCE · 2026-09-17

Dependencies and declared purpose; Git commit e2b2554 by donald7.

SOURCE · 2026-09-17

Upstream transcription call and CUDA-to-CPU fallback.

SOURCE · 2026-09-17

Timing, velocity and overlap processing.

SOURCE · 2026-09-17

Queue, state transitions, deduplication and saved library.

SOURCE · 2026-09-17
CONTINUE IN INTERACTIVE TOOLS, LEARNING & WRITING

Sandbox: browser code experiments