Update app.py

app.py

@@ -2,119 +2,43 @@ import gradio as gr
 from transformers import pipeline
 import soundfile as sf
 import os
-import logging
 
-# Set up logging to help debug issues
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-# Initialize the classifier with error handling
+# --- Model Loading ---
 try:
-    # Using a more reliable emotion classification model
-    classifier = pipeline(
-        "audio-classification", 
-        model="ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition",
-        return_all_scores=True
-    )
-    logger.info("Model loaded successfully")
+    classifier = pipeline("audio-classification", model="superb/wav2vec2-base-superb-er")
 except Exception as e:
-    logger.error(f"Failed to load primary model: {e}")
-    try:
-        # Fallback to a different model
-        classifier = pipeline(
-            "audio-classification",
-            model="superb/wav2vec2-base-superb-er",
-            return_all_scores=True
-        )
-        logger.info("Fallback model loaded successfully")
-    except Exception as e2:
-        logger.error(f"Failed to load fallback model: {e2}")
-        classifier = None
+    def error_fn(audio_file):
+        return {"error": f"Failed to load the model. Please check the logs. Error: {str(e)}"}
+    classifier = None
 
+# --- Prediction Function ---
 def predict_emotion(audio_file):
-    """
-    Predict emotion from audio file
-    """
-    if classifier is None:
-        return {"error": "The AI model could not be loaded. Please check the logs."}
-    
-    if audio_file is None:
-        return {"error": "No audio input provided."}
-    
-    temp_audio_path = None
-    
+    if classifier is None: return {"error": "The AI model could not be loaded."}
+    if audio_file is None: return {"error": "No audio input provided."}
+    if isinstance(audio_file, str): audio_path = audio_file
+    elif isinstance(audio_file, tuple):
+        sample_rate, audio_array = audio_file
+        temp_audio_path = "temp_audio_from_mic.wav"
+        sf.write(temp_audio_path, audio_array, sample_rate)
+        audio_path = temp_audio_path
+    else: return {"error": f"Invalid audio input format: {type(audio_file)}"}
     try:
-        # Handle different input types
-        if isinstance(audio_file, str):
-            audio_path = audio_file
-        elif isinstance(audio_file, tuple):
-            sample_rate, audio_array = audio_file
-            temp_audio_path = "temp_audio_from_mic.wav"
-            sf.write(temp_audio_path, audio_array, sample_rate)
-            audio_path = temp_audio_path
-        else:
-            return {"error": f"Invalid audio input format: {type(audio_file)}"}
-        
-        # Check if file exists
-        if not os.path.exists(audio_path):
-            return {"error": "Audio file not found"}
-        
-        # Perform emotion classification
-        logger.info(f"Processing audio file: {audio_path}")
-        results = classifier(audio_path)
-        
-        # Process results
-        if isinstance(results, list) and len(results) > 0:
-            # Sort by score and return top 5
-            sorted_results = sorted(results, key=lambda x: x['score'], reverse=True)[:5]
-            emotion_scores = {item['label']: round(item['score'], 3) for item in sorted_results}
-        else:
-            return {"error": "No valid results from the model"}
-        
-        logger.info(f"Prediction successful: {emotion_scores}")
-        return emotion_scores
-        
-    except Exception as e:
-        logger.error(f"Error during prediction: {str(e)}")
-        return {"error": f"An error occurred during prediction: {str(e)}"}
-    
+        results = classifier(audio_path, top_k=5)
+        return {item['label']: round(item['score'], 3) for item in results}
+    except Exception as e: return {"error": f"An error occurred during prediction: {str(e)}"}
     finally:
-        # Clean up temporary file
-        if temp_audio_path and os.path.exists(temp_audio_path):
-            try:
-                os.remove(temp_audio_path)
-                logger.info("Temporary audio file cleaned up")
-            except Exception as e:
-                logger.warning(f"Failed to clean up temp file: {e}")
+        if 'temp_audio_path' in locals() and os.path.exists(temp_audio_path): os.remove(temp_audio_path)
 
-# Create Gradio interface
+# --- Gradio Interface ---
 iface = gr.Interface(
     fn=predict_emotion,
-    inputs=gr.Audio(
-        sources=["microphone", "upload"], 
-        type="filepath", 
-        label="Upload Audio or Record with Microphone"
-    ),
-    outputs=gr.Label(
-        num_top_classes=5, 
-        label="Emotion Probabilities"
-    ),
-    title="🎵 AI Audio Emotion Detector",
-    description="Upload an audio file or record your voice to detect emotions. Supported formats: WAV, MP3, M4A, FLAC.",
-    article="This tool uses advanced AI models to analyze emotional content in speech and audio.",
-    examples=None,  # You can add example audio files here if you have them
-    allow_flagging="never"
+    inputs=gr.Audio(sources=["microphone", "upload"], type="filepath", label="Upload Audio or Record with Microphone"),
+    outputs=gr.Label(num_top_classes=5, label="Emotion Probabilities"),
+    title="AI Audio Emotion Detector",
+    description="Upload an audio file or record your voice to detect emotions.",
 )
 
+# Launch the Gradio app with explicit server settings
 if __name__ == "__main__":
-    try:
-        # Launch with queue for better handling of concurrent requests
-        iface.queue(max_size=10).launch(
-            server_name="0.0.0.0",  # Allow external access
-            server_port=7860,       # Default Gradio port
-            share=True,             # Create a public link
-            debug=True              # Enable debug mode
-        )
-    except Exception as e:
-        logger.error(f"Failed to launch Gradio app: {e}")
-        print(f"Error launching app: {e}")
+    # This is the final, most robust way to launch for public access
+    iface.queue().launch(server_name="0.0.0.0", share=True)