Update audio_features.py

audio_features.py

@@ -4,10 +4,10 @@ import librosa
 SR = 16000
 N_COEFFS = 20
 
-def extract_mfcc(y, sr=SR, n_mfcc=N_COEFFS):
+def extract_mfcc(y, sr, n_mfcc=N_COEFFS):
     return librosa.feature.mfcc(y=y, sr=sr, n_mfcc=n_mfcc)
 
-def extract_lfcc(y, sr=SR, n_lfcc=N_COEFFS):
+def extract_lfcc(y, sr, n_lfcc=N_COEFFS):
     S = librosa.feature.melspectrogram(y=y, sr=sr, n_mels=n_lfcc, fmin=0, fmax=sr/2)
     return librosa.power_to_db(S)
 
@@ -15,7 +15,6 @@ def extract_features_with_time_series(file_path, sr=SR, n_coeffs=N_COEFFS):
     try:
         y, _ = librosa.load(file_path, sr=sr, mono=True)
         y, _ = librosa.effects.trim(y)
-
         if np.max(np.abs(y)) > 0:
             y = y / np.max(np.abs(y))
 
@@ -28,11 +27,9 @@ def extract_features_with_time_series(file_path, sr=SR, n_coeffs=N_COEFFS):
 
         features_to_stack = [mfccs, lfccs, chroma, spec_centroid, spec_bandwidth, zcr]
         max_len = max(f.shape[1] for f in features_to_stack)
-        padded_features = [librosa.util.fix_length(f, size=max_len, axis=1) for f in features_to_stack]
-
-        stacked_features = np.vstack(padded_features).astype(np.float32)
+        padded = [librosa.util.fix_length(f, size=max_len, axis=1) for f in features_to_stack]
+        stacked_features = np.vstack(padded).astype(np.float32)
         return stacked_features.T
-
     except Exception as e:
-        print(f"[extract_features] Error processing {file_path}: {e}")
-        return None
+        print(f"[extract_features] Error: {e}")
+        return None