Spaces:
Running
Running
| from __future__ import annotations | |
| import spaces # imported first, as ZeroGPU requires | |
| from pathlib import Path | |
| from tempfile import mkdtemp | |
| import gradio as gr | |
| from pyharp import LabelList, MidiLabel, ModelCard, build_endpoint | |
| from pyharp.tags import Subcategory | |
| from runtime import generate, load_model | |
| model_card = ModelCard( | |
| name="MuseMorphose", | |
| description=( | |
| "Transform piano music with controls for rhythmic intensity and " | |
| "polyphonicity. The MIDI is read as one piano part in 4/4, on a grid of sixteenth notes, " | |
| "with drums left out. The code is MIT, but the checkpoint is CC-BY-4.0, which requires " | |
| "attribution. Repository: https://github.com/YatingMusic/MuseMorphose " | |
| "Paper: https://arxiv.org/abs/2105.04090" | |
| ), | |
| author="Shih-Lun Wu and Yi-Hsuan Yang", | |
| tags=[Subcategory.EDITING, 'style-transfer', 'piano'], | |
| ) | |
| def process_fn( | |
| midi_path, | |
| start_bar, | |
| bars, | |
| rhythm_shift, | |
| poly_shift, | |
| temperature, | |
| top_p, | |
| seed, | |
| ): | |
| # Checked before the GPU is reserved, so a request the model cannot take spends none of the | |
| # caller's ZeroGPU allowance | |
| if not midi_path: | |
| raise gr.Error("Provide the MIDI to transform.") | |
| if int(bars) > 4: | |
| raise gr.Error("Choose at most four bars per request.") | |
| if not 0.5 <= temperature <= 2 or not 0 < top_p <= 1: | |
| raise gr.Error("Temperature or top-p is out of range.") | |
| reference, transformed, generated_remi, details = transform( | |
| midi_path, start_bar, bars, rhythm_shift, poly_shift, temperature, top_p, seed | |
| ) | |
| # HARP reads a JSON output as labels, so the details are one label at the start of the result | |
| labels = LabelList() | |
| labels.append(MidiLabel( | |
| t=0.0, | |
| label=f"{details['generated_notes']} notes in {int(bars)} bars from bar {int(start_bar)}", | |
| description=f"{details['generated_events']} REMI events generated", | |
| )) | |
| return reference, transformed, generated_remi, labels | |
| def transform(midi_path, start_bar, bars, rhythm_shift, poly_shift, temperature, top_p, seed): | |
| try: | |
| # mkdtemp, not a context manager: that would delete the directory on | |
| # exit, taking the three files with it before the caller can read | |
| # them, which is what the block-cache calls here were working around. | |
| # Those also reached for the output component list, which exists only | |
| # under __main__ and so is undefined in the worker that imports this. | |
| reference, transformed, generated_remi, details = generate( | |
| midi_path, | |
| start_bar, | |
| int(bars), | |
| rhythm_shift, | |
| poly_shift, | |
| temperature, | |
| top_p, | |
| seed, | |
| Path(mkdtemp(prefix="musemorphose-")), | |
| ) | |
| except Exception as exc: | |
| raise gr.Error(f"MuseMorphose generation failed: {exc}") from exc | |
| return reference, transformed, generated_remi, details | |
| # pyharp runs process_fn in a worker, which imports this file as __mp_main__ and starts with the | |
| # server, so the model is loaded there, before the first request rather than during it. | |
| if __name__ != "__main__": | |
| load_model() | |
| if __name__ == "__main__": | |
| with gr.Blocks(title="MuseMorphose", delete_cache=(3600, 86400)) as demo: | |
| gr.Markdown("## MuseMorphose piano transformation") | |
| inputs = [ | |
| gr.File( | |
| type="filepath", | |
| file_types=[".mid", ".midi"], | |
| label="Input MIDI", | |
| ).harp_required(True).set_info( | |
| "Piano music to transform. Every pitched track is merged into one piano part, " | |
| "read in 4/4 on a grid of sixteenth notes, and drums are left out." | |
| ), | |
| ] | |
| inputs.extend( | |
| [ | |
| gr.Number(value=0, minimum=0, maximum=9999, precision=0, label="Start bar", | |
| info="The first bar to transform, counting from 0."), | |
| gr.Dropdown( | |
| choices=["1", "2", "3", "4"], value="1", label="Number of bars", | |
| info="How many bars to transform, counting from the start bar.", | |
| ), | |
| gr.Slider(-3, 3, step=1, value=0, label="Rhythmic intensity shift", | |
| info="Steps by which to raise or lower each bar's rhythmic intensity, " | |
| "on the model's scale of 0 to 7. Higher values give busier " | |
| "rhythms."), | |
| gr.Slider(-3, 3, step=1, value=0, label="Polyphonicity shift", | |
| info="Steps by which to raise or lower each bar's polyphony, on the " | |
| "model's scale of 0 to 7. Higher values sound more notes at once."), | |
| gr.Slider(0.5, 2.0, step=0.1, value=1.2, label="Temperature", | |
| info="Sampling randomness. Higher values give more varied but less " | |
| "stable playing."), | |
| gr.Slider(0.1, 1.0, step=0.05, value=0.9, label="Top-p", | |
| info="Samples only from the likeliest tokens whose probabilities add " | |
| "up to this. Lower values stay closer to the likeliest playing."), | |
| gr.Number( | |
| value=0, minimum=0, maximum=2_147_483_647, precision=0, label="Seed", | |
| info="Use the same seed to reproduce a result.", | |
| ), | |
| ] | |
| ) | |
| outputs = [ | |
| gr.File(type="filepath", label="Reference MIDI", file_types=[".mid", ".midi"]).set_info(( | |
| "The chosen bars as uploaded, rendered as MIDI for comparison with the " | |
| "transformed ones." | |
| )), | |
| gr.File(type="filepath", label="Transformed MIDI", file_types=[".mid", ".midi"]).set_info(( | |
| "The restyled performance." | |
| )), | |
| gr.File(type="filepath", label="Generated REMI events", file_types=[".remi"]).set_info(( | |
| "The raw REMI token sequence behind the MIDI, for inspection." | |
| )), | |
| gr.JSON(label="Generation details").set_info( | |
| "A label summarizing what was generated." | |
| ), | |
| ] | |
| build_endpoint( | |
| model_card=model_card, | |
| input_components=inputs, | |
| output_components=outputs, | |
| process_fn=process_fn, | |
| ) | |
| demo.queue(default_concurrency_limit=1, max_size=8).launch(pwa=True, show_error=True) | |