app.py

"""
Copyright (c) Meta Platforms, Inc. and affiliates.
All rights reserved.

This source code is licensed under the license found in the
LICENSE file in the root directory of this source tree.
"""

import torch
import gradio as gr
from hf_loading import get_pretrained


MODEL = None


def load_model(version):
    print("Loading model", version)
    return get_pretrained(version)


def predict(model, text, melody, duration, topk, topp, temperature, cfg_coef):
    global MODEL
    topk = int(topk)
    if MODEL is None or MODEL.name != model:
        MODEL = load_model(model)

    if duration > MODEL.lm.cfg.dataset.segment_duration:
        raise gr.Error("MusicGen currently supports durations of up to 30 seconds!")
    MODEL.set_generation_params(
        use_sampling=True,
        top_k=topk,
        top_p=topp,
        temperature=temperature,
        cfg_coef=cfg_coef,
        duration=duration,
    )

    if melody:
        sr, melody = melody[0], torch.from_numpy(melody[1]).to(MODEL.device).float().t().unsqueeze(0)
        print(melody.shape)
        if melody.dim() == 2:
            melody = melody[None]
        melody = melody[..., :int(sr * MODEL.lm.cfg.dataset.segment_duration)]
        output = MODEL.generate_with_chroma(
            descriptions=[text],
            melody_wavs=melody,
            melody_sample_rate=sr,
            progress=False
        )
    else:
        output = MODEL.generate(descriptions=[text], progress=False)

    output = output.detach().cpu().numpy()
    return MODEL.sample_rate, output


with gr.Blocks() as demo:
    gr.Markdown(
        """
        # MusicGen

        This is the demo for MusicGen, a simple and controllable model for music generation presented at: "Simple and Controllable Music Generation".

        Below we present 3 model variations:
        1. Melody -- a music generation model capable of generating music condition on text and melody inputs. **Note**, you can also use text only.
        2. Small -- a 300M transformer decoder conditioned on text only.
        3. Medium -- a 1.5B transformer decoder conditioned on text only.
        4. Large -- a 3.3B transformer decoder conditioned on text only (might OOM for the longest sequences.)

        When the optional melody conditioning wav is provided, the model will extract
        a broad melody and try to follow it in the generated samples.

        For skipping queue, you can duplicate this space, and upgrade to GPU in the settings.
        <br/>
        <a href="https://huggingface.co/spaces/musicgen/MusicGen?duplicate=true">
        <img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
        </p>

        See [github.com/facebookresearch/audiocraft](https://github.com/facebookresearch/audiocraft)
        for more details.
        """
    )
    with gr.Row():
        with gr.Column():
            with gr.Row():
                text = gr.Text(label="Input Text", interactive=True)
                melody = gr.Audio(source="upload", type="numpy", label="Melody Condition (optional)", interactive=True)
            with gr.Row():
                submit = gr.Button("Submit")
            with gr.Row():
                model = gr.Radio(["melody", "medium", "small", "large"], label="Model", value="melody", interactive=True)
            with gr.Row():
                duration = gr.Slider(minimum=1, maximum=30, value=10, label="Duration", interactive=True)
            with gr.Row():
                topk = gr.Number(label="Top-k", value=250, interactive=True)
                topp = gr.Number(label="Top-p", value=0, interactive=True)
                temperature = gr.Number(label="Temperature", value=1.0, interactive=True)
                cfg_coef = gr.Number(label="Classifier Free Guidance", value=3.0, interactive=True)
        with gr.Column():
            output = gr.Audio(label="Generated Music", type="numpy")
    submit.click(predict, inputs=[model, text, melody, duration, topk, topp, temperature, cfg_coef], outputs=[output])
    gr.Examples(
        fn=predict,
        examples=[
            [
                "An 80s driving pop song with heavy drums and synth pads in the background",
                "./assets/bach.mp3",
                "melody"
            ],
            [
                "90s rock song with electric guitar and heavy drums",
                None,
                "medium"
            ],
            [
                "a light and cheerly EDM track, with syncopated drums, aery pads, and strong emotions",
                "./assets/bach.mp3",
                "melody"
            ],
            [
                "lofi slow bpm electro chill with organic samples",
                "medium",
            ],
        ],
        inputs=[text, melody, model],
        outputs=[output]
    )

demo.launch()