def get_start_positions()

in src/diarizers/data/preprocess.py [0:0]

• 9 lines of code
• 2 McCabe index (conditional complexity)

    def get_start_positions(self, file, overlap, random=False):
        """Get start positions from the audio_chunks in the input audio file.

        Args:
            file (dict): dataset row containing the "audio" feature.
            overlap (float, optional):  Overlap between successive start positions.
            random (bool, optional):  Whether or not to randomly select chunks in the audio file. Defaults to False.

        Returns:
            start_positions: Numpy array containing the start positions of the audio chunks in file.
        """

        sample_rate = file["audio"][0]["sampling_rate"]

        assert sample_rate == self.sample_rate

        file_duration = len(file["audio"][0]["array"]) / sample_rate
        start_positions = np.arange(0, file_duration - self.chunk_duration, self.chunk_duration * (1 - overlap))

        if random:
            nb_samples = int(file_duration / self.chunk_duration)
            start_positions = np.random.uniform(0, file_duration, nb_samples)

        return start_positions