app.py

import gradio as gr
def segment(audio):
    pass  # Implement your image segmentation model here...
demo = gr.Blocks()
with demo:
    gr.Markdown("# **<p align='center'>DIFF-SVC Inference</p>**")

    gr.Markdown(
        """
        <p style='text-align: center'>
        Render whatever model you want with this space!
        </p>
        """
    )
    gr.File(label= 'Load your CKPT')
    
    audio_file = gr.Audio(label = 'Load your WAV', type="filepath")
    gr.Slider(2, 20, value=4)
    b1 = gr.Button("Render")
    #b1.click(speech_to_text, inputs=audio_file, outputs=text)
demo.launch()