xenova-transformers

A production ready for speech-to-text & text translation that runs entirely in your browser: record or upload audio, transcribe with Whisper-style models, translate into many languages, & export results—without sending audio or transcripts to an app server for processing. Heavy ML runs in Web Workers via Transformers.js & ONNX Runtime web

AI-Powered RAG Chatbot

Dhruva.ai - Your guiding star in the academic universe. A multilingual campus chatbot that answers student queries anytime, anywhere.

A RAG chat app for Formula One.

FuseMeld uses AI embeddings to detect semantically similar GitHub issues - not just keyword matches. Plus a narrative timeline of your repo's commit history.

XethScribe is an AI-driven web application designed for real-time audio transcription and translation, leveraging advanced models like OpenAI Whisper for speech recognition. It seamlessly processes audio inputs to deliver accurate, timestamped text outputs for various use cases.

CMMV module for LLM integration, tokenization, RAG dataset creation, and fast FAISS-based vector search for code indexing.

Personal knowledge management app with AI-powered vector search.

Doodle Smith, an ML-powered web game that runs completely in your browser, thanks to Transformers.js!

This PWA offers a fully offline inference runtime with a chat model finetuned from Cerebras-GPT 111M

A responsive and feature-rich AI chatbot built with React.js, TensorFlow.js, and Universal Sentence Encoder. This chatbot can handle queries, provide answers, and learn from user input dynamically.

Created during a 48-hour hackathon (AI for Change @ Virtual), Quick Extract is a text summarization tool that uses the Xenova Transformers library for AI-based text summarization, aiming to enhance reading efficiency. Future updates may focus on improving performance and upgrading the model.

Text-to-speech converter app using Xenova/speecht5_tts

AI-powered semantic matching system that leverages local embedding technology (via @xenova/transformers) and Pinecone's vector database to perform intelligent matching based on skills, experience, and job requirements.

Local-first plagiarism detection tool for educators. Built with Next.js, SQLite, and on-device embeddings to compare student submissions using diff-based similarity and semantic matching—no external APIs required. Upload PDFs, run instant checks, and review results via matrix views, ranked scores, and side-by-side evidence.

Qdrant ile RAG teknolojisinin nasıl uygulanacağını gösteren bir örnektir.

The chrome extension that gets input images and generates the captions for them.

P2P chat with AI, inbox and more

Career Align AI - Skill Matcher and Recommender