Update README.md

README.md

@@ -63,21 +63,6 @@ class CustomDataset(torch.utils.data.Dataset):
         """
         return len(self.dataset)
 
-    def _cutorpad(self, audio: np.ndarray) -> np.ndarray:
-        """
-        Cut or pad audio to the wished length
-        """
-        effective_length = self.sampling_rate * self.max_audio_len
-        len_audio = len(audio)
-
-        # If audio length is bigger than wished audio length
-        if len_audio > effective_length:
-            audio = audio[:effective_length]
-
-        # Expand one dimension related to the channel dimension
-        return audio
-
-
     def __getitem__(self, index):
         if self.basedir is None:
             filepath = self.dataset[index]
@@ -177,7 +162,7 @@ def get_gender(model_name_or_path: str, audio_paths: List[str], label2id: Dict,
         id2label=id2label,
     )
 
-    test_dataset = CustomDataset(audio_paths, max_audio_len=300)  # for 5-minute audio
+    test_dataset = CustomDataset(audio_paths, max_audio_len=5)  # for 5-second audio
 
     data_collator = CollateFunc(
         processor=feature_extractor,