main.py

import os

import gradio as gr

from utils import (
    generate_song,
    remove_last_instrument,
    regenerate_last_instrument,
    change_tempo,
)


os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"

DESCRIPTION = """

# 🎵 Multitrack Midi Generator 🎶
This interactive application uses an AI model to generate music sequences based on a chosen genre and various user inputs.

Features:
🎼 Select the genre for the music.
🌡️ Use the "Temperature" slider to adjust the randomness of the music generated (higher values will produce more random outputs).
⏱️ Adjust the "Tempo" slider to change the speed of the music.
🎹 Use the buttons to generate a new song from scratch, continue generation with the current settings, remove the last added instrument, regenerate the last added instrument with a new one, or change the tempo of the current song.
Outputs:
The app outputs the following:

🎧 The audio of the generated song.
📁 A MIDI file of the song.
📊 A plot of the song's sequence.
🎸 A list of the generated instruments.
📝 The text sequence of the song.
Enjoy creating your own AI-generated music! 🎵
"""

genres = ["ROCK", "POP", "OTHER", "R&B/SOUL", "JAZZ", "ELECTRONIC", "RANDOM"]

demo = gr.Blocks()


def run():
    with demo:
        gr.Markdown(DESCRIPTION)
        with gr.Row():
            with gr.Column():
                temp = gr.Slider(
                    minimum=0, maximum=1, step=0.05, value=0.75, label="Temperature"
                )
                genre = gr.Dropdown(
                    choices=genres, value="POP", label="Select the genre"
                )
                with gr.Row():
                    btn_from_scratch = gr.Button("Start from scratch")
                    btn_continue = gr.Button("Continue Generation")
                    btn_remove_last = gr.Button("Remove last instrument")
                    btn_regenerate_last = gr.Button("Regenerate last instrument")
            with gr.Column():
                with gr.Box():
                    audio_output = gr.Video()
                    midi_file = gr.File()
                    with gr.Row():
                        qpm = gr.Slider(
                            minimum=60, maximum=140, step=10, value=120, label="Tempo"
                        )
                        btn_qpm = gr.Button("Change Tempo")
        with gr.Row():
            with gr.Column():
                plot_output = gr.Plot()
            with gr.Column():
                instruments_output = gr.Markdown("# List of generated instruments")
        with gr.Row():
            text_sequence = gr.Text()
            empty_sequence = gr.Text(visible=False)
        with gr.Row():
            num_tokens = gr.Text()
        btn_from_scratch.click(
            fn=generate_song,
            inputs=[genre, temp, empty_sequence, qpm],
            outputs=[
                audio_output,
                midi_file,
                plot_output,
                instruments_output,
                text_sequence,
                num_tokens,
            ],
        )
        btn_continue.click(
            fn=generate_song,
            inputs=[genre, temp, text_sequence, qpm],
            outputs=[
                audio_output,
                midi_file,
                plot_output,
                instruments_output,
                text_sequence,
                num_tokens,
            ],
        )
        btn_remove_last.click(
            fn=remove_last_instrument,
            inputs=[text_sequence, qpm],
            outputs=[
                audio_output,
                midi_file,
                plot_output,
                instruments_output,
                text_sequence,
                num_tokens,
            ],
        )
        btn_regenerate_last.click(
            fn=regenerate_last_instrument,
            inputs=[text_sequence, qpm],
            outputs=[
                audio_output,
                midi_file,
                plot_output,
                instruments_output,
                text_sequence,
                num_tokens,
            ],
        )
        btn_qpm.click(
            fn=change_tempo,
            inputs=[text_sequence, qpm],
            outputs=[
                audio_output,
                midi_file,
                plot_output,
                instruments_output,
                text_sequence,
                num_tokens,
            ],
        )

    demo.launch(server_name="0.0.0.0", server_port=7860)


if __name__ == "__main__":
    run()