Transliteration with Deep Learning
Project description
DeepTranslit: For better transliteration of Indic languages.
Documentation is available at http://bpraneeth.com/docs/deeptranslit
Usage
from deeptranslit import DeepTranslit
transliterator = DeepTranslit('hindi')
# Currently hindi (hi) is the only supported language.
transliterator.transliterate('mai mbbs complete karliya')
[('मैं एमबीबीएस कम्प्लीट करलिया', 4), ('मैं एमबीबीएस कंप्लीट करलिया', 4), ('मैं एमबीबी कम्प्लीट करलिया', 4)]
Notes:
- The dataset is created from various sources (translation corpora, wikipedia parallel titles etc..).
- Transliteration for low resource languages is not an easy task and will never be perfect. This module is still in beta and not perfect.
TODO:
- Add local caching for faster transliteration.
- Support for more languages.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
deeptranslit-1.0.1.tar.gz
(4.7 kB
view hashes)
Built Distribution
Close
Hashes for deeptranslit-1.0.1-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b646f96872fa0f53bdffddb4e0f1a46278c07e8bac7a4418a8a5fac7afcdf655 |
|
MD5 | 4c3e251323798673ce287f54e3d69e39 |
|
BLAKE2b-256 | e3471a66502c3ab0a9652addf0d7a7d4c41a900b4ecce741a79d7f2f48854a7b |