def process_rttm_file()

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

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

    def process_rttm_file(self, path_to_annotations):
        """extract the list of timestamps_start, timestamps_end and speakers
        from an annotations file with path: path_to_annotations.

        Args:
            path_to_annotations (str): path to the annotations file.

        Returns:
            timestamps_start (list):  A list of timestamps indicating the start of each speaker segment.
            timestamps_end (list): A list of timestamps indicating the end of each speaker segment.
            speakers (list): The list of audio speakers, with their order of appearance.
        """

        timestamps_start = []
        timestamps_end = []
        speakers = []

        with open(path_to_annotations, "r") as file:
            lines = file.readlines()
            for line in lines:
                fields = line.split()

                speaker = fields[-3]
                start_time = float(fields[3])
                end_time = start_time + float(fields[4])

                timestamps_start.append(start_time)
                speakers.append(speaker)
                timestamps_end.append(end_time)

        return timestamps_start, timestamps_end, speakers