SAVRN
Search Contact SAVRN

Independent publisher

Sungkyun Chang

mimbres

Music and Audio

Models in Library1
Datasets in Library1
Models on Hugging Face3
Followers27

Models

Model · Audio to audio

spansynth-edit

Sungkyun Chang

Synthesise music from MIDI, or add, remove, and modify notes in a recording by revising its MIDI. SpanSynth-Edit generates the selected region, using surrounding audio for timbre guidance. Try it in your browser: upload audio, transcribe with YourMT3+, edit the piano roll, and generate. See the local web setup to run the app yourself. - CPU inference is also supported. Measured peak VRAM was about 3.9 GiB on a GH200 for synthesis and both editing methods with default settings (20.48 s crop, 16 steps, CFG 2.0). Install PyTorch for your GPU first, then install the CLI without downloading the demo audio: Model and codec weights download automatically on first use. No token is required.…

Open weights apache-2.0 481M parameters diffusers

Datasets

Dataset · Audio to audio

spansynth-edit-gallery

Sungkyun Chang

Finished MIDI-guided music edits made with SpanSynth-Edit. Open a work's shared link to compare the original and edited audio, explore its score, and make an editable copy. Each work has its own folder: - input.wav and output.wav: the original clip and saved generated audio, at 48 kHz mono. - original.mid and edited.mid: the source and edited score, aligned to the clip. - context.wav: the normalized audio used by the model, including the history before the clip. - project.json: the title, description, notes, editing region, generation settings, and piano-roll display settings. Shared links have the form https://mimbres-spansynth-edit.hf.space/?work=FOLDERNAME. An unlisted work is still…

Publicly accessible