Update app_parallel.py

app_parallel.py

@@ -7,48 +7,32 @@ from io import BytesIO
 import asyncio
 
 async def convert_tts(model_name, tts_text, selected_voice, slang_rate, use_uploaded_voice, voice_upload):
-    try:
-        print(f"Starting TTS for text: {tts_text[:50]}...")  # Log the start of processing
-        
-        edge_tts_voice = voice_mapping.get(selected_voice)
-        if not edge_tts_voice:
-            print(f"Invalid voice selected: {selected_voice}")
-            return {"error": f"Invalid voice '{selected_voice}'."}, None
+    edge_tts_voice = voice_mapping.get(selected_voice)
+    if not edge_tts_voice:
+        return {"error": f"Invalid voice '{selected_voice}'."}, None
 
-        voice_upload_file = None
-        if use_uploaded_voice and voice_upload is not None:
-            print("Processing uploaded voice file...")
-            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()
 
-        print("Calling TTS function...")
-        info, edge_output_filename, tts_output_data = await asyncio.wait_for(
-            tts(model_name, tts_text, edge_tts_voice, slang_rate, use_uploaded_voice, voice_upload_file),
-            timeout=60
-        )
-        print("TTS function call completed.")
+    info, edge_tts_output_path, tts_output_data, edge_output_file = await tts(
+        model_name, tts_text, edge_tts_voice, slang_rate, use_uploaded_voice, voice_upload_file
+    )
 
-        if isinstance(info, dict) and "error" in info:
-            print(f"Error returned from TTS function: {info['error']}")
-            return info, None
+    _, audio_output = tts_output_data
 
-        print("Processing TTS output...")
-        tgt_sr, audio_output = tts_output_data
+    audio_bytes = None
+    if isinstance(audio_output, np.ndarray):
+        byte_io = BytesIO()
+        wavfile.write(byte_io, 40000, audio_output)
+        byte_io.seek(0)
+        audio_bytes = byte_io.read()
+    else:
+        audio_bytes = audio_output
 
-        # Clean up the temporary EdgeTTS output file if it exists
-        if edge_output_filename and os.path.exists(edge_output_filename):
-            os.remove(edge_output_filename)
-
-        audio_data_uri = f"data:audio/wav;base64,{base64.b64encode(audio_bytes).decode('utf-8')}"
-        return {"info": info}, audio_data_uri
-
-    except asyncio.TimeoutError:
-        return {"error": "Operation timed out"}, None
-    except asyncio.CancelledError:
-        return {"error": "Operation was cancelled"}, None
-    except Exception as e:
-        print(f"Error in convert_tts: {str(e)}")
-        return {"error": str(e)}, None
+    audio_data_uri = f"data:audio/wav;base64,{base64.b64encode(audio_bytes).decode('utf-8')}"
+    return {"info": info}, audio_data_uri
 
 def get_models():
     return get_model_names()
@@ -68,11 +52,9 @@ iface = gr.Interface(
     ],
     outputs=[
         gr.JSON(label="Info"),
-        gr.Audio(label="Generated Audio", type="numpy")
+        gr.Textbox(label="Audio URI")
     ],
     title="Text-to-Speech Conversion"
-).queue(concurrency_limit=6, max_batch_size=1)
-
-iface.launch()
-
+).queue(default_concurrency_limit=6)  # Set concurrency limit to 6 based on your hardware
 
+iface.launch()