showastresult

app.py

@@ -261,7 +261,7 @@ def detect_music(audio_data):
                 label = result["label"].lower()
                 if any(music_term in label for music_term in ["music", "song", "singing", "instrument"]):
                     music_confidence = max(music_confidence, result["score"])
-            return music_confidence >= 0.5
+            return music_confidence >= 0.5, results
         
         # Second attempt: Use manually loaded model components
         elif 'music_processor' in globals() and 'music_model' in globals():
@@ -284,33 +284,38 @@ def detect_music(audio_data):
             
             # Check for music-related classes
             music_confidence = 0.0
+            results = []
+            
             for i, (value, index) in enumerate(zip(values[0], indices[0])):
                 label = labels[index.item()].lower()
+                score = value.item()
+                results.append({"label": label, "score": score})
+                
                 if any(music_term in label for music_term in ["music", "song", "singing", "instrument"]):
-                    music_confidence = max(music_confidence, value.item())
+                    music_confidence = max(music_confidence, score)
             
-            return music_confidence >= 0.5
+            return music_confidence >= 0.5, results
             
         else:
             raise ValueError("No music detection model available")
             
     except Exception as e:
         print(f"Error in music detection: {str(e)}")
-        return False
+        return False, []
 
 def process_audio(audio_file):
     """Main function to process audio file, classify genre, and generate lyrics."""
     if audio_file is None:
-        return "Please upload an audio file.", None
+        return "Please upload an audio file.", None, None
     
     try:
         # Extract audio features
         audio_data = extract_audio_features(audio_file)
         
         # First check if it's music
-        is_music = detect_music(audio_data)
+        is_music, ast_results = detect_music(audio_data)
         if not is_music:
-            return "The uploaded audio does not appear to be music. Please upload a music file.", None
+            return "The uploaded audio does not appear to be music. Please upload a music file.", None, None
         
         # Classify genre
         top_genres = classify_genre(audio_data)
@@ -325,10 +330,10 @@ def process_audio(audio_file):
         primary_genre, _ = top_genres[0]
         lyrics = generate_lyrics(primary_genre, audio_data["duration"], emotion_results)
         
-        return genre_results, lyrics
+        return genre_results, lyrics, ast_results
     
     except Exception as e:
-        return f"Error processing audio: {str(e)}", None
+        return f"Error processing audio: {str(e)}", None, None
 
 # Create Gradio interface
 with gr.Blocks(title="Music Genre Classifier & Lyrics Generator") as demo:
@@ -343,15 +348,16 @@ with gr.Blocks(title="Music Genre Classifier & Lyrics Generator") as demo:
         with gr.Column():
             genre_output = gr.Textbox(label="Detected Genres", lines=5)
             emotion_output = gr.Textbox(label="Emotion Analysis", lines=5)
+            ast_output = gr.Textbox(label="Audio Classification Results (AST)", lines=5)
             lyrics_output = gr.Textbox(label="Generated Lyrics", lines=15)
     
     def display_results(audio_file):
         if audio_file is None:
-            return "Please upload an audio file.", "No emotion analysis available.", None
+            return "Please upload an audio file.", "No emotion analysis available.", "No audio classification available.", None
         
         try:
-            # Process audio and get genre and lyrics
-            genre_results, lyrics = process_audio(audio_file)
+            # Process audio and get genre, lyrics, and AST results
+            genre_results, lyrics, ast_results = process_audio(audio_file)
             
             # Format emotion analysis results
             emotion_results = music_analyzer.analyze_music(audio_file)
@@ -360,14 +366,19 @@ with gr.Blocks(title="Music Genre Classifier & Lyrics Generator") as demo:
             emotion_text += f"Primary Emotion: {emotion_results['summary']['primary_emotion']}\n"
             emotion_text += f"Primary Theme: {emotion_results['summary']['primary_theme']}"
             
-            return genre_results, emotion_text, lyrics
+            # Format AST classification results
+            ast_text = "Audio Classification Results (AST Model):\n"
+            for result in ast_results[:5]:  # Show top 5 results
+                ast_text += f"{result['label']}: {result['score']*100:.2f}%\n"
+            
+            return genre_results, emotion_text, ast_text, lyrics
         except Exception as e:
-            return f"Error: {str(e)}", "Error in emotion analysis", None
+            return f"Error: {str(e)}", "Error in emotion analysis", "Error in audio classification", None
     
     submit_btn.click(
         fn=display_results,
         inputs=[audio_input],
-        outputs=[genre_output, emotion_output, lyrics_output]
+        outputs=[genre_output, emotion_output, ast_output, lyrics_output]
     )
     
     gr.Markdown("### How it works")

example.py

@@ -21,7 +21,7 @@ def main():
     print(f"Processing audio file: {audio_file}")
     
     # Call the main processing function
-    genre_results, lyrics = process_audio(audio_file)
+    genre_results, lyrics, ast_results = process_audio(audio_file)
     
     # Get emotion analysis results
     emotion_results = music_analyzer.analyze_music(audio_file)
@@ -40,6 +40,12 @@ def main():
     print(f"Primary Emotion: {emotion_results['summary']['primary_emotion']}")
     print(f"Primary Theme: {emotion_results['summary']['primary_theme']}")
     
+    print("\n" + "="*50)
+    print("AUDIO CLASSIFICATION RESULTS (AST):")
+    print("="*50)
+    for result in ast_results[:5]:  # Show top 5 results
+        print(f"{result['label']}: {result['score']*100:.2f}%")
+    
     print("\n" + "="*50)
     print("GENERATED LYRICS:")
     print("="*50)