A tools collection of text frontend for ESPnet tts recipes.
pip install espnet_tts_frontend- Requires cmake and cython
git clone https://github.com/espnet/espnet_tts_frontend
cd espnet_tts_frontend/
python setup.py pyopenjtalk
# OR
# pip install --global-option=pyopenjtalk -e espnet_tts_frontendFIXME(kamo): Support direct installation from git repo.
Derived from https://github.com/keithito/tacotron
>>> import tacotron_cleaner.cleaners
>>> tacotron_cleaner.cleaners.custom_english_cleaners("(Hello-World); & jr. & dr.")
'HELLO WORLD, AND JUNIOR AND DOCTOR'https://github.com/Kyubyong/g2p
>>> from g2p_en import G2p # Automatically run downloading for the first time
[nltk_data] Downloading package averaged_perceptron_tagger to
...
>>> g2p = G2p()
>>> g2p("hello world")
['HH', 'AH0', 'L', 'OW1', ' ', 'W', 'ER1', 'L', 'D']https://github.com/ikegami-yukino/jaconv/
>>> jaconv.normalize("”あらゆる” 現実を 〜 ’すべて’ 自分の ほうへ ねじ曲げたのだ。")
'"あらゆる" 現実を ー \'すべて\' 自分の ほうへ ねじ曲げたのだ。'https://github.com/r9y9/pyopenjtalk
# Automatically run downloading for the first time
>>> pyopenjtalk.g2p("あらゆる 現実を すべて 自分の ほうへ ねじ曲げたのだ。", kana=True)
'アラユル\u3000ゲンジツヲ\u3000スベテ\u3000ジブンノ\u3000ホーエ\u3000ネジマゲタノダ。'
>>> pyopenjtalk.g2p("あらゆる 現実を すべて 自分の ほうへ ねじ曲げたのだ。", kana=False)
'a r a y u r u pau g e N j i ts u o pau s u b e t e pau j i b u N n o pau h o o e pau n e j i m a g e t a n o d a'>>> import vietnamese_cleaner.vietnamese_cleaner
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent