Hiragana/Katakana minimal pair creator

create_pair.py

# create_pair.py
#
# requires pydub installation
# run download.py twice (to get both male and female voices) to create the hiragana-syllables directory

import os
import sys

from pydub import AudioSegment

DIR = 'pairs'
SYLLABLE_DIR = 'hiragana-syllables'
MALE = 'miyazaki'
FEMALE = 'kanako'
pause = AudioSegment.silent(duration=700)

def main():
    if len(sys.argv) != 4:
        print('create_pair.py (M | F) sound1 sound2')
        return
    gender = MALE if sys.argv[1] == 'M' else FEMALE
    sound1 = sys.argv[2]
    sound2 = sys.argv[3]
    new_dir = os.path.join(os.getcwd(), DIR)
    if not os.path.exists(new_dir):
        os.mkdir(new_dir)
    fname = gender + '-' + sound1 + '+' + sound2 + '.mp3'
    first = AudioSegment.from_mp3(os.path.join(SYLLABLE_DIR, gender + '-sound-' + sound1 + '.mp3'))
    second = AudioSegment.from_mp3(os.path.join(SYLLABLE_DIR, gender + '-sound-' + sound2 + '.mp3'))
    new = first * 3 + pause + second * 3 + pause
    new.export(os.path.join(DIR, fname), format='mp3')
    print(f'Created {fname}')

if __name__ == '__main__':
    main()

download.py

# download.py

import os
import requests
import sys

DL_URL = 'http://www.yesjapan.com/online/mp3/'
MALE = 'miyazaki'
FEMALE = 'kanako'
DIR = 'hiragana-syllables'

sounds = [
    'a',
    'i',
    'u',
    'e',
    'o',

    'ka',
    'ki',
    'ku',
    'ke',
    'ko',

    'sa',
    'shi',
    'su',
    'se',
    'so',

    'ta',
    'chi',
    'tsu',
    'te',
    'to',

    'na',
    'ni',
    'nu',
    'ne',
    'no',

    'ha',
    'hi',
    'fu',
    'he',
    'ho',

    'ma',
    'mi',
    'mu',
    'me',
    'mo',

    'ya',
    'yu',
    'yo',

    'ra',
    'ri',
    'ru',
    're',
    'ro',

    'wa',
    'wo',

    'n',

    'ga',
    'gi',
    'gu',
    'ge',
    'go',

    'za',
    'ji',
    'zu',
    'ze',
    'zo',

    'da',
    'de',
    'do',

    'ba',
    'bi',
    'bu',
    'be',
    'bo',

    'pa',
    'pi',
    'pu',
    'pe',
    'po',

    'kya',
    'kyu',
    'kyo',

    'sha',
    'shu',
    'sho',

    'cha',
    'chu',
    'cho',

    'nya',
    'nyu',
    'nyo',

    'hya',
    'hyu',
    'hyo',

    'mya',
    'myu',
    'myo',

    'rya',
    'ryu',
    'ryo',

    'gya',
    'gyu',
    'gyo',

    'ja',
    'ju',
    'jo',

    'bya',
    'byu',
    'byo',

    'pya',
    'pyu',
    'pyo'
]

def main():
    if len(sys.argv) != 2:
        print('download.py (M | F)')
        return
    gender = MALE if sys.argv[1] == 'M' else FEMALE
    new_dir = os.path.join(os.getcwd(), DIR)
    if not os.path.exists(new_dir):
        os.mkdir(new_dir)
    for sound in sounds:
        fname = 'sound-' + sound + '.mp3'
        r = requests.get(DL_URL + gender + '/' + fname)
        fname = gender + '-' + fname
        if r.status_code == 200:
            with open(os.path.join(new_dir, fname), 'wb') as f:
                f.write(r.content)
            print(f'Downloaded {fname}')
        else:
            print(f'Unable to download {sound} sound file')

if __name__ == '__main__':
    main()