Update app.py

app.py

@@ -7,8 +7,18 @@ from io import BytesIO
 import asyncio
 import os
 import tempfile
+from pathlib import Path
 from gradio.data_classes import FileData
 
+# Create necessary directories
+OUTPUTS_DIR = Path(__file__).parent / "outputs"
+TEMP_DIR = Path(__file__).parent / "temp"
+UPLOAD_DIR = Path(__file__).parent / "uploaded"
+
+# Ensure directories exist
+for directory in [OUTPUTS_DIR, TEMP_DIR, UPLOAD_DIR]:
+    directory.mkdir(exist_ok=True)
+
 async def convert_tts(model_name, audio_file, slang_rate):
     if audio_file is None:
         return {"error": "No audio file uploaded."}, None
@@ -30,18 +40,23 @@ async def convert_tts(model_name, audio_file, slang_rate):
         if audio_output is None:
             return {"error": "No audio output generated"}, None
 
-        # Save output to a file in Gradio's file directory
+        # Save output to a file in the outputs directory
         output_filename = f"output_{os.urandom(4).hex()}.wav"
-        output_path = os.path.join("outputs", output_filename)
-        os.makedirs("outputs", exist_ok=True)
+        output_path = str(OUTPUTS_DIR / output_filename)
 
-        if isinstance(audio_output, np.ndarray):
-            wavfile.write(output_path, tgt_sr, audio_output)
-        else:
-            with open(output_path, "wb") as f:
-                f.write(audio_output)
-            
-        return {"info": info}, output_path
+        try:
+            if isinstance(audio_output, np.ndarray):
+                wavfile.write(output_path, tgt_sr, audio_output)
+            else:
+                with open(output_path, "wb") as f:
+                    f.write(audio_output)
+                
+            print(f"Saved output to: {output_path}")
+            return {"info": info}, output_path
+
+        except Exception as save_error:
+            print(f"Error saving output: {save_error}")
+            return {"error": f"Error saving output: {str(save_error)}"}, None
 
     except Exception as e:
         print(f"Error in convert_tts: {str(e)}")
@@ -57,7 +72,7 @@ iface = gr.Interface(
     fn=convert_tts,
     inputs=[
         gr.Dropdown(choices=get_models(), label="Model", interactive=True),
-        gr.Audio(label="Upload Audio", type="filepath", source="upload"),
+        gr.Audio(label="Upload Audio", source="upload"),
         gr.Slider(minimum=0, maximum=1, step=0.01, label="Slang Rate"),
     ],
     outputs=[
@@ -65,20 +80,15 @@ iface = gr.Interface(
         gr.Audio(label="Converted Audio")
     ],
     title="Voice Conversion",
-    examples=[
-        ["mongolian6-male", "example.wav", 0.0],
-    ]
+    analytics_enabled=False,
+    cache_examples=False
 ).queue()
 
 # Launch the interface
 if __name__ == "__main__":
-    # Create output directory
-    os.makedirs("outputs", exist_ok=True)
-    
     iface.launch(
         debug=True,
         show_error=True,
         max_threads=10,
-        share=False,  # Set to True if you want to create a public link
-        root_path="/content" if os.path.exists("/content") else None
+        share=False  # Set to True if you want to create a public link
     )