def __call__()

in training/data.py [0:0]

• 11 lines of code
• 7 McCabe index (conditional complexity)

    def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
        # split inputs and labels since they have to be of different lengths and need
        # different padding methods
        audios = [feature[self.audio_column_name]["array"] for feature in features]
        len_audio = [len(audio) for audio in audios]
        if self.max_length is not None:
            audios = [audio[: min(l, self.max_length)] for audio, l in zip(audios, len_audio)]

        # since resampling has already been performed in the 'load_multiple_datasets' function,
        # a fixed sampling_rate(44100hz) is passed to the feature_extractor.
        sampling_rate = self.feature_extractor.sampling_rate
        batch = self.feature_extractor(
            audios, sampling_rate=sampling_rate, return_tensors="pt", padding=self.padding, max_length=self.max_length
        )
        batch["len_audio"] = torch.tensor(len_audio).unsqueeze(1)
        return batch