app.py

from voicefixer import VoiceFixer
import gradio as gr
voicefixer = VoiceFixer()
def inference(audio):
    voicefixer.restore(input=audio.name, # input wav file path
                    output="output.wav", # output wav file path
                    cuda=False, # whether to use gpu acceleration
                    mode = 1) # You can try out mode 0, 1 to find out the best result
    return 'output.wav'

inputs = gr.inputs.Audio(type="file", label="Input Audio")
outputs =  gr.outputs.Audio(type="file",label="Output Audio")


title = "VITS"
description = "demo for VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech. To use it, simply add your text, or click one of the examples to load them. Read more at the links below."
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2106.06103'>Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech</a> | <a href='https://github.com/jaywalnut310/vits'>Github Repo</a></p>"



gr.Interface(inference, inputs, outputs, title=title, description=description, article=article).launch()