Update app.py

app.py

@@ -40,7 +40,6 @@ def infer(prompt, input_wav_file):
     # Move the WAV file to the new directory
     shutil.move(source_path, os.path.join(destination_path, f"{file_name}.wav"))
 
-
     text = prompt
 
     # with random speaker
@@ -72,27 +71,49 @@ def infer(prompt, input_wav_file):
     for item in contents:
         print(item)   
     
-    return "output.wav", f"bark_voices/{file_name}/{content[1]}"
-
-gr.Interface(
-    fn=infer, 
-    inputs=[
-        gr.Textbox(
+    return "output.wav", f"bark_voices/{file_name}/{contents[1]}"
+
+css = """
+#col-container {max-width: 780px; margin-left: auto; margin-right: auto;}
+"""
+
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        
+        gr.HTML("""
+        <h1>Instant Voice Cloning</h1>
+        """)
+        
+        prompt = gr.Textbox(
             label="Text to speech prompt"
-        ), 
-        gr.Audio(
+        )
+        
+        audio_in = gr.Audio(
             label="WAV voice to clone", 
             type="filepath",
             source="upload"
         )
-    ],
-    outputs=[
-        gr.Audio(
+        
+        submit_btn = gr.Button("Submit")
+        
+        cloned_out = gr.Audio(
             label="Text to speech output"
-        ),
-        gr.File(
+        )
+        
+        npz_file = gr.File(
             label=".npz file"
         )
-    ], 
-    title="Instant Voice Cloning"
-).launch()
+    
+    submit_btn.click(
+        fn = infer,
+        inputs = [
+            prompt,
+            audio_in
+        ],
+        outputs = [
+            cloned_out, 
+            npz_file
+        ]
+    )
+
+demo.queue().launch()