๐ง Project Overview
Lecture Voice-to-Notes Generator is an AI-based tool that automatically converts recorded lecture audio into clean, concise study notes and quizzes. The system uses speech recognition and natural language processing (NLP) to help students focus on learning rather than note-taking. This project was developed as part of the IBM AI Internship Program, demonstrating real-world applications of artificial intelligence in education.
๐ Features
๐๏ธ Speech-to-Text Transcription โ Converts lecture audio into text using Faster Whisper (offline-friendly ASR model). ๐งฉ AI Summarization โ Condenses long transcripts into concise, meaningful notes. ๐ Quiz Generator โ Automatically creates simple fill-in-the-blank questions for quick revision. ๐ฅ๏ธ Streamlit Web Interface โ Simple web UI for uploading, viewing, and downloading notes. ๐พ Offline Support โ Works without continuous internet once models are downloaded.
๐๏ธ System Architecture Audio Input (.mp3 / .wav) โ Speech Recognition (Faster Whisper) โ Summarization (T5 / NLP model) โ Quiz Generation (keyword extraction) โ Output: Notes + Quizzes (Displayed / Downloadable)
๐งฐ Tech Stack Component Technology Used Programming Language Python Speech-to-Text Faster Whisper (Hugging Face) Summarization HuggingFace Transformers (T5) Quiz Generation Custom NLP script Frontend Streamlit Dependencies Torch, Transformers, Pandas, SentencePiece
โ๏ธ How to Run
git clone https://github.com//LectureVoiceToNotes.git cd LectureVoiceToNotes
python -m venv .venv .venv\Scripts\activate # (Windows)
pip install -r requirements.txt
streamlit run app.py
๐ง Sample Usage
Upload your lecture audio (.mp3 or .wav) Wait for automatic transcription View generated: Transcript Summary Quiz questions
๐งพ Example Output
Summary: Photosynthesis is the process where plants convert sunlight into energy using chlorophyll in chloroplasts, producing glucose and oxygen.
Quiz:
Photosynthesis occurs in _____ using chlorophyll. (chloroplasts) The process converts _____ into chemical energy. (sunlight)
๐ Future Enhancements
Add PDF/Word export for generated notes Support for multiple languages Real-time lecture transcription Integration with cloud storage (IBM Cloud / Google Drive)