Create app.py

app.py

@@ -0,0 +1,65 @@
+import gradio as gr
+import base64
+import numpy as np
+from scipy.io import wavfile
+from voice_processing import parallel_tts, get_model_names
+from io import BytesIO
+import asyncio  # Import asyncio
+
+# Define an asynchronous function for the Gradio interface
+async def convert_tts(model_name, audio_file, slang_rate):
+    if audio_file is None:
+        return {"error": "No audio file uploaded."}, None
+
+    try:
+        # Create task for parallel processing
+        task = (model_name, None, None, slang_rate, True, audio_file)
+        
+        # Asynchronous call to processing function
+        result = await asyncio.get_event_loop().run_in_executor(None, parallel_tts, [task])
+        
+        if result[0] is None or len(result[0]) != 3:
+            return {"error": "Processing failed"}, None
+            
+        info, _, (tgt_sr, audio_output) = result[0]
+
+        # Process audio output to bytes
+        if audio_output is None:
+            return {"error": "No audio output generated"}, None
+
+        audio_bytes = None
+        if isinstance(audio_output, np.ndarray):
+            byte_io = BytesIO()
+            wavfile.write(byte_io, tgt_sr, audio_output)
+            byte_io.seek(0)
+            audio_bytes = byte_io.read()
+        else:
+            audio_bytes = audio_output
+
+        audio_data_uri = f"data:audio/wav;base64,{base64.b64encode(audio_bytes).decode('utf-8')}"
+        return {"info": info}, audio_data_uri
+
+    except Exception as e:
+        print(f"Error in convert_tts: {str(e)}")
+        return {"error": str(e)}, None
+
+def get_models():
+    return get_model_names()
+
+# Initialize the Gradio interface
+iface = gr.Interface(
+    fn=convert_tts,
+    inputs=[
+        gr.Dropdown(choices=get_models(), label="Model", interactive=True),
+        gr.Audio(label="Upload Audio", type="filepath"),
+        gr.Slider(minimum=0, maximum=1, step=0.01, label="Slang Rate"),
+    ],
+    outputs=[
+        gr.JSON(label="Info"),
+        gr.Audio(label="Converted Audio")
+    ],
+    title="Voice Conversion"
+).queue()
+
+# Launch the interface with max_threads
+iface.launch(debug=True, max_threads=10)  # Set max_threads to control concurrency