INNER CODE UNIT · Python

transcript_to_list

flashlight/wav2letter · data/librispeech/utils.py:36

def transcript_to_list(file):
    audio_path = os.path.dirname(file)
    ret = []
    with open(file, "r") as f:
        for line in f:
            file_id, trans = line.strip().split(" ", 1)
            audio_file = os.path.abspath(os.path.join(audio_path, file_id + ".flac"))
            duration = sox.file_info.duration(audio_file) * 1000  # miliseconds
            ret.append([file_id, audio_file, str(duration), trans.lower()])

    return ret


def read_list(src, files):
    ret = []
    for file in files:
        with open(os.path.join(src, file + ".lst"), "r") as f:
            for line in f:

View source record →