tabs/audios/ui.py

import gradio as gr

from config import Config
from .events import *


def audio_tab():
    with gr.Row():
        with gr.Column():
            with gr.Group():
                with gr.Group():
                    text = gr.Textbox(lines=5, label="Enter text")
                    language = gr.Dropdown(
                        label="Language",
                        choices=["en"],
                        value="en",
                    )
                
                with gr.Accordion('Voice Clone', open=True):
                    speaker_audio = gr.Audio(label="Upload Audio", type='numpy')
                    clear_speaker_audio = gr.Button(label="Clear Audio")
        
        with gr.Column():
            output_audio = gr.Audio(label="Output Audio", interactive=False, show_download_button=True)
            clear_output_audio = gr.Button(label="Clear Audio")
            generate_audio = gr.Button(label="Generate Audio")
            
            with gr.Accordion('Advance Settings', open=True):
                settings = [
                    ('Alpha', 'tts_alpha', 'float', 0.0, 1.0, 0.3, 0.1,),
                    ('Beta', 'tts_beta', 'float', 0.0, 1.0, 0.7, 0.1,),
                    ('Diffusion Steps', 'tts_diffusion_steps', 'int', 1, 100, 10, 1,),
                    ('Embedding Scale', 'tts_embedding_scale', 'int', 0, 10, 1, 1,),
                ]
                for label, key, type_, min_, max_, value, step in settings:
                    globals()[key] = gr.Slider(label=label, minimum=min_, maximum=max_, value=value, step=step)
    
    
    # Events
    # Clear Audio
    clear_speaker_audio.click(clear_audio, speaker_audio, speaker_audio)
    clear_output_audio.click(clear_audio, output_audio, output_audio)
    
    # Generate Audio
    generate_audio.click(
        gen_audio,
        [text, language, speaker_audio, tts_alpha, tts_beta, tts_diffusion_steps, tts_embedding_scale], # type: ignore
        [output_audio]
    )