[Anubad] Fwd: [smc-discuss] Introducing Varnam

Sankarshan Mukhopadhyay sankarshan.mukhopadhyay at gmail.com
Wed Jun 19 22:53:07 PDT 2013


---------- Forwarded message ----------
From: Navaneeth.K.N <navaneethkn at gmail.com>
Date: Wed, Jun 19, 2013 at 2:31 PM
Subject: [smc-discuss] Introducing Varnam
To: Discussion list of Swathanthra Malayalam Computing
<discuss at lists.smc.org.in>


Hello everyone,

I have developed an open-source, cross platform transliterator for
Indian languages named "Varnam" which works very similar to how Google
transliterate works. More details of the project and an online version
is available at http://varnamproject.com.

"libvarnam" [1] is at the core of all the projects and does the heavy
work. `libvarnam` has a simple frequency based learning module built
in. This can learn words and different patterns which can be used to
input the specified word.

I have implemented Hindi & Malayalam. Hindi support is very recent and
may be not very stable. IMO, Malayalam support is very stable and
works well for most words. It has learned more than half million
Malayalam words so far. If there are some words which "varnam" don't
know, you can input it phonetically and varnam will learn the word.
Varnam also does prefix tokenization which allows it to provide
correct word when only a prefix is known to it. For Malayalam, I am
using mostly Mozhi scheme.

There are some language bindings for libvarnam which enables it's use
from other programming languages like, Javascript [2], Java etc [3].

I am planning to write IMEs, (iBus plugins, Windows IME) etc which
will enable full offline use of this tool. `libvarnam` is very fast,
but the hosting server is openshift's free tier.

Please take it for a spin and let me know how it goes. I'd love to get
some feedback about this.

[1] : https://github.com/navaneeth/libvarnam
[2] : https://github.com/navaneeth/libvarnam-nodejs
[3] : https://github.com/navaneeth/libvarnam-java

--
Cheers
Navaneeth

_______________________________________________
Swathanthra Malayalam Computing discuss Mailing List
Project: https://savannah.nongnu.org/projects/smc
Web: http://smc.org.in | IRC : #smc-project @ freenode
discuss at lists.smc.org.in
http://lists.smc.org.in/listinfo.cgi/discuss-smc.org.in




--
sankarshan mukhopadhyay
<https://twitter.com/#!/sankarshan>



More information about the Anubad mailing list