C

corpus

Resume Analyzer is an open-source tool built with Python that analyzes resumes using NLP and ML. It extracts skills, education, and experience, then matches them with job descriptions to generate similarity scores and recommendations for recruiters and job seekers.

JanaBhasha is an open-source multilingual dictionary and corpus collection platform focused on preserving India's linguistic diversity. It enables users to contribute regional words, folk songs, and stories — both in text and audio. Using AI models like Whisper and Puter, the platform supports real-time transcription and translation.

"SahayaSoochi is a Streamlit-based AI assistant that generates All types of letters in Telugu and English from user text/voice input."

Lok Katha is a corpus data collection app for preserving and sharing proverbs, folk tales, and oral traditions in multiple Indian languages. It allows contributors to submit text and audio, helping build an open, community-driven dataset for research, education, and cultural preservation.

this project is for recalling the old spiritual things

Telugu Meme Remix / Desi Meme Center — a full-stack meme hub to create, remix and share Telugu memes. Live demo: https://app--telugu-meme-remix-c8f05cce.base44.app

AI-powered offline-first Streamlit application for collecting corpus data (audio, video, image+caption, and text) in 11 Indian languages for SOAI 2025.

Jeevitham (meaning Life in Telugu) is a community-driven initiative aimed at building sustainable digital tools that address real-world social, environmental, and livelihood challenges. The project focuses on empowering people with open-source solutions that can be adapted for local needs.

🌱 Vision

To create technology that enhances human life, respects cultural diversity, and ensures sustainability for future generations.

🎯 Objectives

Develop open-source applications that promote sustainability and well-being.

Preserve and integrate local knowledge systems with modern digital platforms.

Provide tools for data collection, visualization, and decision-making in communities.

Encourage collaboration among students, developers, and citizens for social impact.

🔑 Features (example directions — adapt as per your actual files)

📊 Data Logger & Analyzer – record and analyze data (health, environment, livelihood).

🌍 Localization – tools and content in local languages (Telugu + others).

🗂 Templates for Collaboration – pre-built templates for issue tracking and merge requests.

💡 Extensible Design – easy to add new features based on community needs.

🛠️ Tech Stack

Frontend: HTML, CSS, JavaScript (React optional)

Backend: Python / Node.js (based on module)

Database: SQLite / PostgreSQL

Version Control: Git + GitLab

🚀 How to Contribute

Fork the repository.

Create a feature branch.

Add your contributions.

Submit a merge request with the provided template.

📜 License

This project is licensed under AGPLv3 to ensure openness and community benefit.

Cinemoji is a playful, gamified Telugu movie‑trivia app that uses emoji puzzles, rapid‑fire sprints, head‑to‑head challenges, and voice‑dubbing tasks to engage Gen Z in creative, social gameplay. As users guess movies or dub iconic lines, they’re also seeding a rich Telugu language corpus—collecting authentic movie titles, dialogues, slang, and regional dialect samples. This crowd‑driven approach not only delivers addictive, shareable content for young audiences but also powers a data‑collection engine that fuels future AI models with culturally nuanced Telugu text and audio.

Festival Log – A Cultural Corpus Collection Engine

Festival Log is an open-source, AI-powered Streamlit application designed to document and preserve the rich festival traditions of India. Users can submit cultural information, stories, and personal experiences related to festivals in their local language. The app automatically translates each entry into Telugu using open-source AI models and displays all entries in a collective log. It is optimized for low-bandwidth areas, supports multilingual input, and contributes to building a parallel corpus for Indian language AI research.

I want learn about ai and work on the projects