Update video_processing.py

video_processing.py

@@ -8,7 +8,7 @@ from PIL import Image, ImageDraw, ImageFont
 import math
 from face_analysis import get_face_embedding, cluster_faces, organize_faces_by_person, draw_facial_landmarks
 from pose_analysis import pose, calculate_posture_score, draw_pose_landmarks
-from voice_analysis import extract_audio_from_video, diarize_speakers, get_speaker_embeddings
+from voice_analysis import get_speaker_embeddings, align_voice_embeddings
 from anomaly_detection import anomaly_detection
 from visualization import plot_mse, plot_mse_histogram, plot_mse_heatmap, create_video_with_heatmap
 from utils import frame_to_timecode
@@ -154,11 +154,12 @@ def process_video(video_path, anomaly_threshold, desired_fps, progress=None):
         face_samples = get_all_face_samples(organized_faces_folder, output_folder, largest_cluster)
 
         progress(0.8, "Extracting audio and performing voice analysis")
-        
+            
         audio_path = extract_audio_from_video(video_path)
         diarization = diarize_speakers(audio_path)
         voice_embeddings, audio_duration = get_speaker_embeddings(audio_path, diarization, "pyannote/embedding")
 
+        aligned_voice_embeddings = align_voice_embeddings(voice_embeddings, frame_count, original_fps, audio_duration)
 
         progress(0.85, "Performing anomaly detection")
         embedding_columns = [col for col in df.columns if col.startswith('Raw_Embedding_')]
@@ -177,7 +178,7 @@ def process_video(video_path, anomaly_threshold, desired_fps, progress=None):
             X_voice = np.array([emb for emb in aligned_voice_embeddings])
 
             mse_embeddings, mse_posture, mse_voice = anomaly_detection(X_embeddings, X_posture, X_voice)
-            
+        
             progress(0.9, "Generating graphs")
             mse_plot_embeddings, anomaly_frames_embeddings = plot_mse(df, mse_embeddings, "Facial Features",
                                                                       color=GRAPH_COLORS['facial_embeddings'],