Update app.py

app.py

@@ -4,40 +4,48 @@ import numpy as np
 from scipy.io import wavfile
 from voice_processing import parallel_tts, get_model_names, voice_mapping
 from io import BytesIO
-import asyncio  # Import asyncio
+import asyncio
+import logging
+
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+logger = logging.getLogger(__name__)
 
-# Define an asynchronous function for the Gradio interface
 async def convert_tts(model_name, tts_text, selected_voice, slang_rate, use_uploaded_voice, voice_upload):
-    edge_tts_voice = voice_mapping.get(selected_voice)
-    if not edge_tts_voice:
-        return {"error": f"Invalid voice '{selected_voice}'."}, None
+    try:
+        edge_tts_voice = voice_mapping.get(selected_voice)
+        if not edge_tts_voice:
+            raise ValueError(f"Invalid voice '{selected_voice}'.")
+
+        voice_upload_file = None
+        if use_uploaded_voice and voice_upload is not None:
+            with open(voice_upload.name, 'rb') as f:
+                voice_upload_file = f.read()
 
-    voice_upload_file = None
-    if use_uploaded_voice and voice_upload is not None:
-        with open(voice_upload.name, 'rb') as f:
-            voice_upload_file = f.read()
+        # Create task for parallel processing
+        task = (
+            model_name, tts_text, edge_tts_voice, slang_rate, use_uploaded_voice, voice_upload_file
+        )
+        
+        # Asynchronous call to your tts processing function using parallel processing
+        result = await asyncio.get_event_loop().run_in_executor(None, parallel_tts, [task])
+        info, _, (tgt_sr, audio_output) = result[0]
 
-    # Create task for parallel processing
-    task = (
-        model_name, tts_text, edge_tts_voice, slang_rate, use_uploaded_voice, voice_upload_file
-    )
-    
-    # Asynchronous call to your tts processing function using parallel processing
-    result = await asyncio.get_event_loop().run_in_executor(None, parallel_tts, [task])
-    info, _, (tgt_sr, audio_output) = result[0]
+        # Process audio output to bytes
+        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
 
-    # Process audio output to bytes
-    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
 
-    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:
+        logger.exception("Error in convert_tts")
+        return {"error": str(e)}, None
 
 def get_models():
     return get_model_names()
@@ -58,10 +66,11 @@ iface = gr.Interface(
     ],
     outputs=[
         gr.JSON(label="Info"),
-        gr.Textbox(label="Audio URI")
+        gr.Audio(label="Generated Audio", type="uri")
     ],
     title="Text-to-Speech Conversion"
-)
+).queue(concurrency_count=16)  # Adjust based on your server's capacity
 
 # Launch the interface
-iface.launch(debug=True)  # Set share=True to create a public link
+if __name__ == "__main__":
+    iface.launch(debug=True)