ProjectDIGITAL TAMIL .

Something Big is Coming Soon

Finetuning LLM for தமிழ்

A
漢
あ
අ
א
Ω
어
ゑ
அ
யாதும் ஊரே யாவரும் கேளிர்

To us, all towns are one, all men our kin

தமிழ்

Hugging Face01/03

Digital Heritage Corpus

A massive curated dataset of ancient manuscripts and contemporary literature.

GitHub02/03

Thiruppugazh Sandhi

Sophisticated rule-based sandhi decomposition tool for Tamil poetry.

Active Build
GitHub03/03

Tamil Simple OCR

Minimalist, high-accuracy optical character recognition for Tamil scripts.

97.3% Accuracy