NLP

A Streamlit and AI-powered web application for creating Telugu memes and collecting linguistic corpus data

This project is a real-time voice translator web application built with Streamlit. It captures live speech input via microphone, recognizes the spoken text using speech recognition, translates it to a selected target language via machine translation, and plays back the translated audio using text-to-speech synthesis. The app supports multiple languages, provides start/stop controls for continuous conversation flows, displays original and translated text, allows editing of transcriptions, and enables exporting of recordings and analysis. It aims to facilitate accessible, multilingual communication and contribute to language corpora for research purposes.

AI-powered exploration and visualization of ancient Indian texts using NLP and image colorization.

BakBak-Bot

BakBak-Bot is an advanced conversational AI assistant built for linguistic research, machine learning training, and digital archiving purposes. The bot leverages natural language processing (NLP) to understand and respond to user queries in multiple languages, making it an ideal tool for researchers, educators, and developers working on language technologies.

Key Features Multi-language Support: Communicate in various languages Intelligent Conversations: Context-aware responses using NLP Research-Oriented: Designed for linguistic analysis and data collection Digital Archiving: Store and retrieve conversation data efficiently Extensible Architecture: Easy to customize and extend functionality

AI/ML-based tool that predicts the likelihood of diabetes using medical parameters such as glucose, BMI, age, and blood pressure.

Chitra Vani is an AI-driven platform for generating and managing images and media content using intuitive interfaces and automated tools.

AI-powered platform for collecting and analyzing multilingual cultural narratives from global communities, built with Streamlit and Python.

A family recipe sharing app built with Python for managing and sharing recipes across family members.

🎬 Telugu Movie Review Sentiment Analysis using Machine Learning and Flask. Classifies Telugu movie reviews into Positive, Negative, or Neutral. Built as part of the Swecha Internship program for Telugu NLP.

SwechaBot: A conversational AI chatbot built with Streamlit, Hugging Face Transformers, and Torch

Project Description An AI-powered Healthcare LLM designed to assist visually impaired (blind) individuals. The system provides accessible medical guidance through natural language processing, voice interaction, and context-aware support. This project aims to enhance healthcare accessibility, improve independence, and empower blind users by bridging the gap between medical knowledge and inclusivity.

A Streamlit-based music library application that allows users to browse, search, and stream audio tracks according to thier mood and also it is an otp sign in thing where it is integrated with swecha apis. Built with Python and Streamlit, designed for fast deployment.

A fun and educational Streamlit web app to test, learn, and contribute Telugu slang, with Cohere AI-powered auto-suggestions.

name: civicvoice-ai-app description: AI-powered civic engagement tool that summarizes public input and highlights actionable insights for governments. tags:

civic-tech NLP public-engagement AI default_branch: main visibility: public license: AGPL-3.0-only

My-Culture-My-Voice is a cultural AI project using Hugging Face and NLP to preserve Telugu traditions, language, and knowledge.

The "Wisdom Jotter App" is an open-source, AI-powered Streamlit application designed to collaboratively collect proverbs and life-lessons and preserve valuable cultural and experiential knowledge from across India. This application serves as a "Corpus Collection Engine" for Viswam.ai's mission to develop AI that deeply understands India's linguistic and cultural diversity. It allows users to contribute either traditional proverbs or life lessons in their native languages. A core feature is the integration of an open-source AI model, sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2, for semantic duplicate detection. This ensures the collected data is unique, high-quality, and valuable for training future AI models. All contributions are stored securely in Google Sheets, and the app is built with an emphasis on accessibility for users in low-internet bandwidth regions.

AI-MOCK-INTERVIEW is an advanced, AI-powered platform designed to help job seekers practice and enhance their interview skills through realistic mock interviews. The platform leverages AI technologies, including natural language processing (NLP), machine learning, and computer vision, to simulate technical and behavioral interviews tailored to the user’s experience level and job role. It features dynamic question generation, real-time performance evaluation, speech and video analysis for verbal and non-verbal feedback, and detailed actionable insights to boost candidate confidence and readiness. Built with modern frameworks and tools, this project offers a scalable and interactive approach to preparation, suitable for candidates at various career stages.

Fitzor Bot is an open-source AI-powered fitness assistant that helps users stay healthy and active. It provides personalized workout recommendations, tracks fitness progress, answers health-related queries, and motivates users to achieve their goals. Built using Python, NLP, and chatbot frameworks, Fitzor Bot is designed for gyms, trainers, and individuals seeking smart health guidance.

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.

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.