README.en.md

🌉 VideoLingo: Bridging Languages in Every Frame

中文 | English

🍖 Fully automated video localization: Seamlessly generate translated and dubbed videos from English video links!

QQ Group: 875297969

🌟 What We Offer

• 🎬 Netflix-quality subtitles: Say goodbye to amateur translations!

• 🎤 Clone your own voice for dubbing!

• ✨ Click-and-done in Streamlit!

Check out our demo! 🚀💪

ted_demo_sub.mp4

You can also use GPT-SoVITS to add your own voice!

ted_demo_dubbing.mp4

Features

• 📚 NLP and LLM-driven subtitle segmentation

• 🧠 Intelligent terminology knowledge base for context-aware translation

• 🔄 Three-step translation process: Direct translation - Reflection - Improvement

• 🎯 Precise word-level subtitle alignment

• 💰 Extremely low cost: Create 5 minutes of cross-language subtitles for just 0.1 yuan

• 🎤 High-quality personalized dubbing with GPT-SoVits

• 👨‍💻 Developer-friendly: Step-by-step structured files for easy customization: English Guide | Chinese Guide

Hardware Requirements

• Tested on Mac M1 Pro 16G and Windows RTX4060

🎯 How to Use

1. Download the one-click startup package: Click here (Windows only, not widely tested. Mac users please install from source)

2. Configure the api_key in config.py

3. Click OnekeyLaunch.bat to start Streamlit!

🚀 Installation from Scratch

Note: This installation guide is applicable for Mac and Windows systems

1. Clone the repository:

   git clone https://github.com/Huanshere/VideoLingo.git
   cd VideoLingo

2. Set up and activate the Conda virtual environment:

   conda create -n videolingo python=3.12.0
   conda activate videolingo

3. Configure config.py

4. Run the installation script:

   python install.py

5. 🎉 Launch Streamlit!

   streamlit run st.py

🙏 Acknowledgements

Thanks to the following open-source projects for their contributions:

• whisper: OpenAI's open-source automatic speech recognition system
• whisper-timestamped: Extension adding timestamp functionality to Whisper
• yt-dlp: Command-line tool for downloading YouTube videos and content from other websites
• GPT-SoVITS & GPT-SoVITS-Inference: Speech synthesis system based on GPT and SoVITS, and its inference library
• FFmpeg: Complete cross-platform solution for handling multimedia content
• Ultimate Vocal Remover GUI v5 (UVR5): Tool for separating vocals and instrumentals in music
• json_repair: Super powerful library for repairing and parsing GPT's JSON output, seamlessly replacing json.loads

Star History