{"slug": "lecturelens-mozhi-ask-your-lectures-anything-fully-offline-with-whisper-gemma", "title": "LectureLens (Mozhi): Ask Your Lectures Anything, Fully Offline with Whisper, Gemma and ChromaDB", "summary": "A four-person team built LectureLens (Mozhi), an offline study tool that turns lecture recordings and documents into summaries, key terms, quizzes and grounded Q&A with timestamp or page citations. The system runs entirely on a laptop using faster-whisper for timestamped transcription, Gemma via Ollama for generation, multilingual-e5-small sentence-transformers embeddings, ChromaDB as the vector store, and a Gradio interface, with no API keys or cloud services. Answers are restricted to the uploaded material and the tool states when a lecture does not cover a question rather than guessing.", "body_md": "LectureLens (Mozhi) turns a lecture recording or document into a study resource. You upload audio, a PDF, a Word file, a text file or an image, choose the language, and get a summary, key terms and a quiz. Then you can ask questions, and every answer comes only from your material and shows where it came from: a timestamp for audio, a page or section for documents. If the lecture doesn't cover the question, it says so instead of guessing.\n\nEverything runs locally on a laptop with open-source tools, with no API keys and no cloud.\n\n[https://github.com/bavishnu11/hacktoberfest-hack-day-coimbatore-x-init-club-and-idea-club](https://github.com/bavishnu11/hacktoberfest-hack-day-coimbatore-x-init-club-and-idea-club)\n\n`faster-whisper` transcribes audio with timestamps. PDFs, Word files, text files and images are read into page- or section-labelled pieces.\n| Part | Tool | \n|---|---|\n| Speech to text | faster-whisper | \n| LLM | Gemma via Ollama | \n| Embeddings | sentence-transformers (multilingual-e5-small) | \n| Vector store | ChromaDB | \n| UI | Gradio | \n\n[This runs fully open-source AI models locally—using faster-whisper for timestamped speech-to-text transcription and Gemma via Ollama for grounded Q&A, summaries, and quizzes.]\n\n[Managing local performance constraints when running compute-heavy open-source AI models (faster-whisper and Gemma via Ollama) and ensuring strict RAG grounding. Practical experience in building modular end-to-end RAG pipelines with vector databases (ChromaDB), optimizing local multilingual embeddings, and structuring prompt constraints for accurate JSON quiz generation and local LLM orchestration.]\n\n| Member | Contribution | \n|---|---|\n| Sanjay Vijay | faster-whisper transcription, timestamps, language setting, transcript cleanup | \n| Sujithbabu S S | Chunking, embeddings, ChromaDB, search function with timestamp metadata | \n| Vishal P | Ollama setup, summary, key terms, quiz, Q&A prompt, multilingual answers | \n| S J Bavishnu | Gradio app, repo and Git workflow, README, demo video, deployment, pitch |", "url": "https://wpnews.pro/news/lecturelens-mozhi-ask-your-lectures-anything-fully-offline-with-whisper-gemma", "canonical_source": "https://dev.to/sanjayvijay0112/lecturelens-mozhi-ask-your-lectures-anything-fully-offline-with-whisper-gemma-and-chromadb-51n3", "published_at": "2026-10-08 10:37:03+00:00", "updated_at": "2026-10-08 10:49:16.934137+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "natural-language-processing", "ai-products", "developer-tools"], "entities": ["LectureLens", "Mozhi", "faster-whisper", "Gemma", "Ollama", "ChromaDB", "sentence-transformers", "Gradio"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/lecturelens-mozhi-ask-your-lectures-anything-fully-offline-with-whisper-gemma", "markdown": "https://wpnews.pro/news/lecturelens-mozhi-ask-your-lectures-anything-fully-offline-with-whisper-gemma.md", "text": "https://wpnews.pro/news/lecturelens-mozhi-ask-your-lectures-anything-fully-offline-with-whisper-gemma.txt", "jsonld": "https://wpnews.pro/news/lecturelens-mozhi-ask-your-lectures-anything-fully-offline-with-whisper-gemma.jsonld"}}