Create app.py

app.py

@@ -0,0 +1,35 @@
+import os
+import shutil
+import zipfile
+import gradio as gr
+
+os.chdir('ParallelWaveGAN/')
+os.system('pip install -e .')
+os.chdir('..')
+os.system('gdown https://drive.google.com/uc?id=1Flw6Z0K2QdRrTn5F-gVt6HdR9TRPiaKy')
+
+shutil.move('VQMIVC-pretrained models/checkpoints/', '.')
+shutil.move('VQMIVC-pretrained models/vocoder/', '.')
+
+with zipfile.ZipFile('/content/VQMIVC/VQMIVC-pretrained models.zip', 'r') as zip_ref:
+    zip_ref.extractall('/content/VQMIVC/')
+
+def inference(audio1, audio2):
+  os.system("python convert_example.py -s "+ audio1.name+" -r "+ audio2.name+ " -c converted -m 'checkpoints/useCSMITrue_useCPMITrue_usePSMITrue_useAmpTrue/VQMIVC-model.ckpt-500.pt'")
+  out = os.path.basename(str(audio1)).split(".")[0] + "_converted_gen.wav"
+  return out
+
+inputs = [gr.inputs.Audio(label="Source Audio", type=file),gr.inputs.Audio(label="Reference Audio", type=file)]
+outputs =  gr.outputs.Audio(label="Output Audio", type=file)
+
+
+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>"
+
+examples = [
+ ["We propose VITS, Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech."],
+ ["Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling."]   
+]
+
+gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=examples).launch()