This project is an AI-powered tool that transcribes audio files from various sources, including YouTube videos and other downloaded audio/video formats. The transcriptions are saved to a Chroma database for storage and retrieval.
- Audio/Video Transcription: Automatically transcribes audio from YouTube videos and other audio/video files.
- Chroma Database Integration: Transcriptions are stored in a Chroma database.
- Transcription Summarization: Provides concise summaries of the transcriptions to quickly extract key information in a short form.
- RAG-Enabled ChatBot: Includes a user-friendly interface built with Streamlit. Users can interact with the chatbot, which leverages Retrieval-Augmented-Generation (RAG) to answer questions about the transcriptions or video content.
- Transcribe and summarize long audio or video content for research or note-taking.
- Ask questions about the video or transcription through a chatbot interface, powered by RAG to provide context-aware answers.
- Efficiently manage large amounts of transcribed data using the Chroma database.
- Clone the repository.
- Install the required dependencies.
- Navigate to the local repository in terminal or command prompt
- Enter
streamlit run lecture_summarizer.py
This tool is perfect for anyone who needs an AI assistant to help with transcribing and summarizing large volumes of video or audio content while allowing for intuitive querying through a chatbot interface.