def get_segments_in_file()

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

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

    def get_segments_in_file(self, file, labels):
        """Get segments in file.

        Args:
            file (_type_): dataset row from input dataset.
            labels (_type_):  a list of all speakers in the audio file.

        Returns:
            annotations (numpy array): _description_
        """

        file_annotations = []

        for i in range(len(file["timestamps_start"][0])):
            start_segment = file["timestamps_start"][0][i]
            end_segment = file["timestamps_end"][0][i]
            label = labels.index(file["speakers"][0][i])
            file_annotations.append((start_segment, end_segment, label))

        dtype = [("start", "<f4"), ("end", "<f4"), ("labels", "i1")]

        annotations = np.array(file_annotations, dtype)

        return annotations