Update voice_analysis.py

voice_analysis.py

@@ -23,7 +23,13 @@ def extract_voice_features(audio_path, segment_duration=1000):
     
     return np.array(segments)
 
+def remove_nan_features(features):
+    return features[~np.isnan(features).any(axis=1)]
+
 def cluster_voices(features):
+    # Remove NaN values
+    features = remove_nan_features(features)
+    
     if len(features) < 2:
         print("Not enough voice segments for clustering. Assigning all to one cluster.")
         return np.zeros(len(features), dtype=int)
@@ -43,6 +49,7 @@ def get_most_frequent_voice(features, clusters):
 
 def process_audio(audio_path, segment_duration=1000):
     features = extract_voice_features(audio_path, segment_duration)
+    features = remove_nan_features(features)
     clusters = cluster_voices(features)
     most_frequent_voice = get_most_frequent_voice(features, clusters)
     return most_frequent_voice, features, clusters