{"id":24792595,"url":"https://github.com/praths71018/video_text_summarisation_and_prompting","last_synced_at":"2026-04-25T16:34:16.154Z","repository":{"id":258909597,"uuid":"875880924","full_name":"praths71018/Video_Text_Summarisation_And_Prompting","owner":"praths71018","description":"An application where you upload a video in the webapp and it provides a summary of the video. You can also interact with the video by prompting ","archived":false,"fork":false,"pushed_at":"2025-01-30T10:23:11.000Z","size":32475,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-24T15:31:21.797Z","etag":null,"topics":["audio-transcription","chatbot","flask","image-capture","langchain","llm","nlp-machine-learning","prompt-engineering","prompting","question-answering","rag","reactjs","summarization","transcript","translation","video-gpt","video-processing"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/praths71018.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-10-21T03:01:29.000Z","updated_at":"2025-01-30T10:23:15.000Z","dependencies_parsed_at":"2024-10-21T06:45:20.336Z","dependency_job_id":null,"html_url":"https://github.com/praths71018/Video_Text_Summarisation_And_Prompting","commit_stats":null,"previous_names":["praths71018/video_text_summarisation_and_prompting"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/praths71018/Video_Text_Summarisation_And_Prompting","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/praths71018%2FVideo_Text_Summarisation_And_Prompting","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/praths71018%2FVideo_Text_Summarisation_And_Prompting/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/praths71018%2FVideo_Text_Summarisation_And_Prompting/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/praths71018%2FVideo_Text_Summarisation_And_Prompting/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/praths71018","download_url":"https://codeload.github.com/praths71018/Video_Text_Summarisation_And_Prompting/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/praths71018%2FVideo_Text_Summarisation_And_Prompting/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32269462,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-25T09:15:33.318Z","status":"ssl_error","status_checked_at":"2026-04-25T09:15:31.997Z","response_time":59,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["audio-transcription","chatbot","flask","image-capture","langchain","llm","nlp-machine-learning","prompt-engineering","prompting","question-answering","rag","reactjs","summarization","transcript","translation","video-gpt","video-processing"],"created_at":"2025-01-29T20:38:01.090Z","updated_at":"2026-04-25T16:34:16.131Z","avatar_url":"https://github.com/praths71018.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# **GlobalLearn: A VideoGPT**  \n\n## **Table of Contents**\n1. [Introduction](#introduction)  \n2. [Features](#features)  \n3. [Methodology](#methodology)  \n4. [Results](#results)  \n5. [Installation and Usage](#installation-and-usage)  \n6. [Contributors](#contributors)  \n7. [Demo Video](#Demo-Video)\n\n---\n\n## **Introduction**\nGlobalLearn is an educational application that **summarizes educational videos** into text format in **multiple languages** and allows users to **prompt questions** based on the video content.  \n\nThe app uses **audio and image processing techniques** to extract text and generate a concise summary. Additionally, a **Retrieval-Augmented Generation (RAG) model** is implemented to answer user queries based on the extracted text.  \n\n---\n\n## **Features**\n- **Automatic Video Summarization**: Converts video content into structured text.  \n- **Multimodal Data Extraction**:\n  - **Audio-based transcript extraction**  \n  - **Image-based text extraction (when audio is unavailable)**  \n- **Multi-Language Support**: Summarized text can be translated into various languages.  \n- **Question-Answering System**: Users can prompt questions and receive answers based on the video content.  \n- **Efficient Processing**: Generates summaries quickly, even in CPU runtime environments.  \n\n---\n\n## **Methodology**\n![Methodology](assets/Methodology.png)\n### **1. Data Collection \u0026 Preprocessing**\n- Collect videos from a single subject.  \n- Convert video into **audio and image frames**.  \n- Extract **transcripts from audio**.  \n- Extract **text from images** (when audio is muted).  \n- Clean and structure the extracted text.  \n\n### **2. Knowledge Base Construction**\n- Combine text from **audio \u0026 images**.  \n- Create a **Retrieval-Augmented Generation (RAG) corpus** to facilitate question answering.  \n\n### **3. Summarization \u0026 Translation**\n- Generate a **concise summary** of the extracted text.  \n- Provide translations into multiple languages.  \n\n### **4. User Interface \u0026 Deployment**\n- Build an interface to **upload videos \u0026 prompt questions**.  \n- Deploy a **server** to run all models and functionalities.  \n\n---\n\n## **Results**\n- **TF-IDF Similarity Score**: **0.46**  \n  - Ensures key terms are used without copying transcript structure.  \n- **Semantic Similarity Score**: **0.82**  \n  - Ensures summaries retain meaning while using different sentence structures.  \n- **Processing Time**:\n  - For a **10-minute video**, summary generation takes around **4 minutes** on a **CPU-based system**.  \n\n### **Key Outcomes**\n✅ Works with videos that **lack transcripts**.  \n✅ Combines **audio \u0026 image-based text extraction**.  \n✅ Supports **multilingual summaries**.  \n✅ Enables **question-answering based on video content**.  \n\n---\n\n## **Installation and Usage**\n### **Prerequisites**\n- Python 3.x  \n- Required libraries (install via `requirements.txt`)  \n\n### **Installation**\n```bash\ngit clone https://github.com/praths71018/Video_Text_Summarisation_And_Prompting.git\ncd Video_Text_Summarisation_And_Prompting\n```\n\n### **Running the Application**\n1. Go to the backend directory and create a virtual environment:\n   ```bash\n   cd backend\n   python -m venv venv\n   ```\n2. Activate the virtual environment:\n   ```bash\n   source venv/bin/activate\n    ```\n3. Install requirements:\n   ```bash\n   pip install -r requirements.txt\n   ```\n4. **Start the backend server**:\n   ```bash\n   python backend/app.py\n   ```\n5. Activate the **frontend**:\n   ```bash\n   cd frontend\n   npm install\n   npm start\n   ```\n5. **Upload a video** through the web interface.\n6. **Wait for processing** (transcription, summarization, translation).\n7. **Ask questions** based on the generated summary.\n\n---\n\n## **Contributors**\n- **Pratham R Shetty**  \n- **Prateek M**\n- **R Ranjive**\n- **Anirudh Krishna**\n\n---\n\n# Demo Video\n[DemoVideo.mp4](assets/DemoVideo.mp4)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpraths71018%2Fvideo_text_summarisation_and_prompting","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpraths71018%2Fvideo_text_summarisation_and_prompting","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpraths71018%2Fvideo_text_summarisation_and_prompting/lists"}