Update app.py

app.py

@@ -12,11 +12,11 @@ def process_and_show_completion(video_input_path, anomaly_threshold_input, fps,
         print("Starting video processing...")
         results = process_video(video_input_path, anomaly_threshold_input, fps, progress=progress)
         print("Video processing completed.")
-
+    
         if isinstance(results[0], str) and results[0].startswith("Error"):
             print(f"Error occurred: {results[0]}")
-            return [results[0]] + [None] * 25
-
+            return [results[0]] + [None] * 27  # Increased to 27 to account for the new audio waveform plot
+    
         exec_time, results_summary, df, mse_embeddings, mse_posture, mse_voice, \
             mse_plot_embeddings, mse_plot_posture, mse_plot_voice, \
             mse_histogram_embeddings, mse_histogram_posture, mse_histogram_voice, \
@@ -24,13 +24,12 @@ def process_and_show_completion(video_input_path, anomaly_threshold_input, fps,
             face_samples_frequent, \
             anomaly_faces_embeddings, anomaly_frames_posture_images, \
             aligned_faces_folder, frames_folder, \
-            stacked_heatmap = results
-
+            stacked_heatmap, audio_waveform_plot = results
+    
         anomaly_faces_embeddings_pil = [Image.fromarray(face) for face in anomaly_faces_embeddings] if anomaly_faces_embeddings is not None else []
         anomaly_frames_posture_pil = [Image.fromarray(frame) for frame in anomaly_frames_posture_images] if anomaly_frames_posture_images is not None else []
-
         face_samples_frequent = [Image.open(path) for path in face_samples_frequent] if face_samples_frequent is not None else []
-
+    
         output = [
             exec_time, results_summary,
             df, mse_embeddings, mse_posture, mse_voice,
@@ -41,17 +40,17 @@ def process_and_show_completion(video_input_path, anomaly_threshold_input, fps,
             face_samples_frequent,
             aligned_faces_folder, frames_folder,
             mse_embeddings, mse_posture, mse_voice,
-            stacked_heatmap  
+            stacked_heatmap,
+            audio_waveform_plot
         ]
-
         return output
-
+    
     except Exception as e:
         error_message = f"An error occurred: {str(e)}"
         print(error_message)
         import traceback
         traceback.print_exc()
-        return [error_message] + [None] * 25
+        return [error_message] + [None] * 26 
 
 def show_results(outputs):
     return gr.Group(visible=True)
@@ -93,6 +92,7 @@ with gr.Blocks() as iface:
                 anomaly_frames_posture = gr.Gallery(label="Anomaly Frames (Body Posture)", columns=6, rows=2, height="auto")
 
             with gr.TabItem("Voice"):
+                audio_waveform_plot = gr.Plot(label="Audio Waveform")
                 mse_voice_plot = gr.Plot(label="MSE: Voice")
                 mse_voice_hist = gr.Plot(label="MSE Distribution: Voice")
                 mse_voice_heatmap = gr.Plot(label="MSE Heatmap: Voice")
@@ -219,7 +219,7 @@ with gr.Blocks() as iface:
             face_samples_most_frequent,
             aligned_faces_folder_store, frames_folder_store,
             mse_heatmap_embeddings_store, mse_heatmap_posture_store, mse_heatmap_voice_store,
-            stacked_heatmap_plot  
+            audio_waveform_plot, stacked_heatmap_plot  
         ]
     ).then(
         show_results,