Skip to content

Latest commit

 

History

History
78 lines (61 loc) · 2.39 KB

Languages.md

File metadata and controls

78 lines (61 loc) · 2.39 KB

Google Input Tools - Transliteration scripts

Transliterate from romanized text to any of the following languages.

Note:

  • Google Input Tools actually uses back-transliteration models for conversion.
    • Hence it might not produce good results for English language words, because English is phonetically impure (In English, pronounciations vary from the way we write it in Latin alphabet)

Languages Supported

(Source)

Indic scripts

Language ISO639 Code
Assamese (অসমীয়া) as
Bengali (বাংলা) bn
Gujarati (ગુજરાતી) gu
Hindi (हिन्दी) hi
Kannada (ಕನ್ನಡ) kn
Malayalam (മലയാളം) ml
Marathi (मराठी) mr
Nepali (नेपाली) ne
Oriya (ଓଡ଼ିଆ) or
Punjabi (ਪੰਜਾਬੀ) pa
Sanskrit (संस्कृतम्) sa
Sinhala (සිංහල) si
Tamil (தமிழ்) ta
Telugu (తెలుగు) te

Cyrillic scripts

Language ISO639 Code
Belarusian (беларуски) be
Bulgarian (български) bg
Russian (русский) ru
Serbian (српски) sr
Ukranian (украї́нська) uk

PersoArabic scripts

Language ISO639 Code
Arabic (عَرَبِيّ) ar
Persian (فارسی) fa
Urdu (اُردُو) ur

More scripts

Language ISO639 Code
Amharic (አማርኛ) am
Greek (ελληνικά) el
Hebrew (עִבְרִית‎) he
Japanese (日本語) ja
Thai (ภาษาไทย) th
Tigrinya (ትግርኛ) ti

Chinese scripts

Language Usage Code Supported Input Schemes
Simplified Chinsese (Zhōngwén) zh pinyin, pinyin-x0-shuangpin-abc, pinyin-x0-shuangpin-ms, pinyin-x0-shuangpin-flypy, pinyin-x0-shuangpin-jiajia, pinyin-x0-shuangpin-ziguang, pinyin-x0-shuangpin-ziranma, wubi-1986
Traditional Chinese (Taiwan) zh-hant pinyin, cangjie-1982
Yue (HongKong Chinese) yue-hant jyutping, und

Note:

  • und means undefined, by which Google uses default transliterator.

Chinese Usage

from google.transliteration import transliterate_text
result = transliterate_text('Zen', lang_code='zh', input_scheme='pinyin')
print(result)