Awesome List of Tamil NLP & AI Resources
-
Updated
Apr 6, 2023 - HTML
#
tamil-nlp
Here are 20 public repositories matching this topic...
OCR Tamil is a powerful tool that can detect and recognize text in Tamil images with high accuracy on Natural Scenes
python natural-language-processing ocr computer-vision transformer tamil optical-character-recognition indic-scripts handwriting-recognition handwritten-text-recognition indic-languages ocr-recognition scene-text-recognition scene-text-detection ocr-python scene-text-detection-recognition tamil-language tamil-nlp tamil-ocr ocr-tamil
-
Updated
Sep 6, 2025 - Python
ThamizhiMorph: A Tamil Morphological Analyser and Generator
morphological-analyser foma stanza finite-state-transducers morphological-generator tamil-language tamil-nlp
-
Updated
May 6, 2026 - Python
Tamizh language parser, grammatical tools, utils, and more
-
Updated
Mar 10, 2024 - Java
ThamizhiPOSt - A neural based POS tagger for Tamil
-
Updated
Jan 11, 2021 - Python
KuralGen generates Thirukkural for a given English sentence
-
Updated
Mar 6, 2024 - Python
Repo that analyses the frequency of words in Tamil
frequency word corpus corpus-linguistics corpus-data tamil word-count indian-language south-indian tamil-language tamil-nlp tamil-words tamil-frequency tamil-word-count tamil-corpus
-
Updated
Jul 4, 2023 - Python
A Python suite of Tamil NLP tools.
-
Updated
May 30, 2021 - Python
A content-based movie recommendation system using Natural Language Processing (NLP) techniques on Tamil movie reviews. The system utilizes TF-IDF vectorization and cosine similarity to suggest movies based on user preferences or input reviews.
nlp text-classification scikit-learn tf-idf cosine-similarity movie-recommendation content-based-filtering tamil-nlp
-
Updated
Apr 18, 2025 - Jupyter Notebook
-
Updated
Dec 3, 2019 - Jupyter Notebook
Multilingual homophobia and transphobia detection in Tamil and Malayalam using mBERT with a Streamlit-based demo
nlp deep-learning text-classification transformers hate-speech-detection streamlit tamil-nlp mbert multilingual-nlp homophobia-detection transphobia-detection malayalam-nlp
-
Updated
Apr 29, 2026 - Jupyter Notebook
SiMaSeVaKuGa LLM — Sovereign Tamil Language Model. A robust vLLM/sLLM platform optimized for Indian linguistic contexts, capable of understanding, generating, and reasoning in Tamil
-
Updated
Aug 2, 2026 - Python
GPT-2 Architecture, Dravidian Models- Tamil, Telugu, Kannada, Malayalam
nlp transformers language-modeling computational-linguistics tokenization low-resource-languages gpt-2 huggingface pretraining tamil-nlp dravidian-languages kannada-nlp telugu-nlp malayalam-nlp
-
Updated
Aug 21, 2026 - Python
A structured, open dataset archiving over 250,000 Sri Lankan news articles across Sinhala, Tamil, and English media outlets
data-science archive dataset srilanka sinhala-nlp onthisday tamil-nlp news-archival srilanka-data sl-news srilanka-news
-
Updated
Aug 23, 2026 - Shell
Simple Chatbot to get thirukkural by Number or keyword with English explanation.
-
Updated
Mar 19, 2025 - Python
தமிழ் AI கட்டளை வடிவமைப்பு கையேடு — Open-source Tamil Prompt Engineering Handbook with 200+ ready-to-use prompt templates across 10+ roles (developers, poets, marketers, educators & more). Frameworks: CLEAR, CRAFT, AUTOMAT, CATS.
-
Updated
May 16, 2026 - Mermaid
A Morphological Transducer for the Jaffna Tamil dialect
-
Updated
Aug 27, 2026 - Shell
A script to calculate frequency of words from Tamil text for CS4661: Natural Language Processing
-
Updated
Jun 29, 2024 - Python
An enterprise-grade, local-first AI assistant engineered for the Erode District Collectorate (Tamil Nadu) to automate bilingual administrative workflows, document summarization, grievance handling, and analytics with zero data leakage.
react python govtech ai-assistants fastapi sovereignty tamil-nlp district-administrative-units olloma sovereign-ai
-
Updated
Aug 31, 2026 - Python
An MCP server for grounded Tamil word-grammar (சொல் இலக்கணம்) analysis — classify native vs. borrowed words, find roots and meanings, and suggest pure-Tamil equivalents. Answers are anchored in authentic sources (Tholkappiyam) and self-enrich from evolving Tamil data. Built for native speakers.
python nlp mcp morphology computational-linguistics tamil morphological-analysis finite-state-transducers low-resource-languages tamil-language tamil-nlp model-context-protocol fastmcp tamil-language-processing tholkappiyam
-
Updated
Aug 21, 2026 - Python
Add this topic to your repo
To associate your repository with the tamil-nlp topic, visit your repo's landing page and select "manage topics."