datasets/spd_datasets.py [104:129]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def get_sakura_files(path_to_sakura, convert_mp4_to_mp3=False):

    if convert_mp4_to_mp3:
        audio_files = glob.glob(path_to_sakura + "/sakura/audio/*.mp4")

        for mp4_path in audio_files:

            mp3_path = mp4_path.split(".")[0] + ".mp3"

            MP4ToMP3(mp4_path, mp3_path)

    audio_files = glob.glob(path_to_sakura + "/sakura/audio/*.mp3")

    audio_files = {
        "data": audio_files,
    }
    cha_files = {
        "data": [],
    }

    for subset in audio_files:
        for cha_path in audio_files[subset]:
            file = cha_path.split("/")[-1].split(".")[0]
            cha_files[subset].append(path_to_sakura + "/sakura/cha/{}.cha".format(file))

    return audio_files, cha_files
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



datasets/spd_datasets.py [166:191]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def get_sakura_files(path_to_sakura, convert_mp4_to_mp3=False):

    if convert_mp4_to_mp3:
        audio_files = glob.glob(path_to_sakura + "/sakura/audio/*.mp4")

        for mp4_path in audio_files:

            mp3_path = mp4_path.split(".")[0] + ".mp3"

            MP4ToMP3(mp4_path, mp3_path)

    audio_files = glob.glob(path_to_sakura + "/sakura/audio/*.mp3")

    audio_files = {
        "data": audio_files,
    }
    cha_files = {
        "data": [],
    }

    for subset in audio_files:
        for cha_path in audio_files[subset]:
            file = cha_path.split("/")[-1].split(".")[0]
            cha_files[subset].append(path_to_sakura + "/sakura/cha/{}.cha".format(file))

    return audio_files, cha_files
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -