muscriptor-studio / README.md
Mike0021's picture
Add one-click synthetic audio examples
010a4f9 verified
|
Raw
History Blame
1.46 kB
metadata
title: MuScriptor Studio
emoji: 🎼
colorFrom: gray
colorTo: indigo
sdk: gradio
sdk_version: 6.10.0
app_file: app.py
short_description: Multi-instrument audio transcription to editable MIDI
startup_duration_timeout: 1h

MuScriptor Studio

A custom ZeroGPU interface for MuScriptor, the multi-instrument audio-to-MIDI model from Kyutai and Mirelo.

The app runs the 307M-parameter medium checkpoint, streams transcription progress after each 5-second audio window, renders an interactive color-coded piano roll, and exports both the full arrangement and isolated instrument MIDI files.

Three one-click example sessions are included: a synth-funk groove, a drumless glass arpeggio, and a clockwork 3/4 waltz. They are original procedural recordings made entirely from generated oscillators and seeded noise, with no third-party samples. Example results are cached lazily after first use so startup never consumes ZeroGPU quota.

The checkpoint is gated under CC BY-NC 4.0. This Space requires an HF_TOKEN secret whose owner has accepted access to MuScriptor/muscriptor-medium.

API

The Gradio endpoint is /transcribe. It accepts an audio file, optional exact instrument group names, a sampling toggle, and temperature. It returns the combined MIDI, all isolated track files, the browser visualization payload, and a machine-readable manifest.