open-tamil

open-tamil copied to clipboard

OpenTamilWeb app - demo the classifier for English vs Tamil transliterated words

2

SciKitLearn classifier is present in the examples of OpenTamil to classify if given sequence of Tamil letters is English transliteration or original Tamil letters. e.g. காழ்ப்பு -vs- பக்கெட்

arcturusannamalai

Unigram data from Project Madurai, Wikipedia

1

Collect Unigram data from Project Madurai, Wikipedia

arcturusannamalai

OpenTamilWebApp demo - numeral generation audio [m/f] voice generation can be shown via the HTML tag and WAV synthesis module in Open-Tamil examples code. It would be a nice example...

arcturusannamalai

தமிழ் - ஆங்கிலம் ஒருங்கிணைந்த சொல் அகராதி

1

Parallel corpora for Tamil. இது இருந்தால் "organic" என்ற சொல்லை "ஒர்கனிக்" என்று தமிழில் ஒலி மாற்றி எழுதினால், இதனை நாம் "இயற்கையான" என்று தமிழ்படுத்துவதற்கு உதவும்.

arcturusannamalai

Improve sandhi checker

2


abuvanth

transliterate - use quillpad.in rules and files

3

http://www.quillpad.in gives better transliteration for tamil. its source is here. https://github.com/CognirelTech/Quillpad-Server Make use of its xml files and rules to add better transliteration for open-tamil

tshrinivasan

suggestion- make NLTK for tamil

4

please make NLTK pos taggers and corpus reader etc... for tamil language.

abuvanth

Add reST documentation for open-tamil classes/methods

2

Continue work started by @arulalant to add reST docs for open-tamil classes and methods. Currently the following modules are exported to user as API via pip install. 1. tamil 2....

arcturusannamalai

translation english to tamil

1

exact translation of english to tamil and tamil to english . not like google translator.

abuvanth

Emacs auto-lang mode to detect Tamil

1

Auto lang mode needs a list of most common Tamil words https://github.com/emacsmirror/auto-lang

arcturusannamalai