Update prosody_preprocessor.py

prosody_preprocessor.py

@@ -97,6 +97,7 @@ class ProsodyPreprocessor(FeatureExtractionMixin):
     def extract_features(self, audio):
         """Extract F0 and intensity features"""
         print(f"audio", audio)
+        print('Extracting features')
         audio = torch.Tensor(audio)
 
         if audio.dim() == 1:
@@ -105,9 +106,9 @@ class ProsodyPreprocessor(FeatureExtractionMixin):
         f0 = f0[0, 0, :]
         f0_interpolated = f0_interp[0, 0, :]
         
-        # Remove first 5 frames as in original
-        f0 = f0[5:]
-        f0_interpolated = f0_interpolated[5:]
+        
+        f0 = f0[6:]
+        f0_interpolated = f0_interpolated[6:]
 
         sound = parselmouth.Sound(audio.numpy(), sampling_frequency=self.sampling_rate, start_time=0)
         print(f"Sound duration: {sound.duration} seconds")