indic-translit 0.1.3.1

Transliterate to and from Indian languages. Currently supported Dravida languages - ಕతెമத.

Tools to transliterate from and detransliterate to Dravidian languages (Kannada, Malayalam, Tamil, and Telugu).

Sub-Modules

transliterate

Contains the function transliterate. Given a file (text or pickle) and the script, this function transliterates from the provided script and saves it in the specified file.

detransliterate

Contains the function detransliterate. Given a file (text or pickle) and the script, this function detransliterates to the required script and saves it in the specified file.

Classes

Transliterator

Defines the class Transliterator, which transliterates TaKaMaTe into Latin.

DeTransliterator

Defines the class DeTransliterator, which detransliterates TaKaMaTe from Latin.

Quick Start

import indic_translit as translit
from translit.Transliterator import Transliterator
from translit.DeTransliterator import DeTransliterator

transliterator = Transliterator("Telugu")
text = u'ప్రియాంక విప్పారిత నేత్రాలతో త్రినాధ్ కేసే మౌనంగా చూస్తుండి పోయింది.'
trans_text = transliterator.transliterate(text)
print(trans_text)
# priyāṁka vippārita nētrālatō trinādh kēsē maunaṁgā cūstuṁḍi pōyiṁdi.

detransliterator = DeTransliterator("Telugu")
re_text = detransliterator.detransliterate(trans_text)
print(re_text)
# ప్రియాంక విప్పారిత నేత్రాలతో త్రినాధ్ కేసే మౌనంగా చూస్తుండి పోయింది.

Known Issues

1. The (de)transliterations output for Malayalam are not one-to-one due to different representations for the same sound, such as ൿ and ക്, ർ and റ്, ൻ and ന്. Feedback is sought for the correctness of the current state and what needs to be done to make them correct. There are no known issues for the remaining languages. The community is encouraged to report more issues.

License

MIT