Skip to content

degubites/voice2text

Repository files navigation

Project Alttl - Vid2Summary

example

🌍 Languages:
🇺🇸 English | 🇰🇷 한국어 | 🇨🇳 中文 | 🇯🇵 日本語

💡 What is Project Alttl?

Project Alttl is an open-source initiative dedicated to creating software that helps people save money and live more efficiently. Whether it's through automation, cost-cutting solutions, or smarter financial tools, our goal is to make technology work for your life.

🚀 Vid2Summary - Features

  • AI-powered (OpenAI Whisper) text summarization from video/audio files
  • Multi-language support (English, Korean, Chinese, Japanese)
  • User-friendly GUI built with Flet (powered by Flutter)

🖥️ Requirements

Hardware

  • Minimum GPU: NVIDIA graphics card with 6GB VRAM
  • Recommended GPU: NVIDIA RTX graphics card with 8GB+ VRAM

Software

  • NVIDIA Graphics Driver (Latest version)
  • NVIDIA CUDA 11.8
  • Python 3.10
  • Required Python Modules: See requirements.txt

📥 Installation & Usage

  1. Clone the repository:

    git clone https://github.com/yourusername/Vid2Summary.git
    cd Vid2Summary
  2. Create and activate a virtual environment (recommended):

    python -m venv .venv
    # On Windows:
    .venv\Scripts\activate
    # On macOS/Linux:
    source .venv/bin/activate
  3. Install dependencies:

    pip install -r requirements.txt
  4. Run the application:

    • On Windows: Double-click run.bat or run from command prompt:
      .\run.bat
    • On macOS/Linux: Make run.sh executable and run:
      chmod +x run.sh
      ./run.sh
    • Note: Running via these scripts ensures that the application runs within its isolated Python environment, which helps with dependency management and debugging. Error logs from the application will be visible in the console where the script is run.

🚀 How to Use

  1. Select Save Folder: Click the "저장할 폴더 선택" (Select save folder) button to choose where the transcribed text files will be saved.
  2. Upload Files:
    • Drag & Drop (Experimental): You can try dragging and dropping video/audio files onto the application window. (Note: This feature might not work consistently on all systems.)
    • Select Files: Click the "파일 선택" (Select files) button to open a file dialog and choose one or more video/audio files (.mp4, .avi, .mkv, .mp3, .wav, .ogg).
  3. Transcription: The application will automatically process the selected files and save the transcribed text to the chosen folder.

⬇️ Download

This project is intended to be run from source. Please follow the installation and usage instructions above.

About

A simple and efficient tool to extract text from videos using OpenAI Whisper, designed for multilingual support and user convenience.

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages