timminator/VideOCR v1.4.1

VideOCR v1.4.1

on GitHub

Highlights:

• Lowered default ocr_image_max_width value to speed up high-res video processing
• GUI gets properly resized and positioned if size extends Workarea
• Improve progress update rate to inform the user about the current status
• Drop AVX2/FMA requirement

Fixes:

• Fixed output for right to left languages
• Fixed post completion action commands
• Fixed a bug where the GUI would not minimize when clicking its taskbar icon

Main Highlights of the v1.4.x release:

• Integrates the latest PaddleOCR 3.4 version which extends support to 110 languages and provides increased accurary for latin, cyrillic, arabic etc.
• Adds support for batch processing
• Preprocessing step for vfr videos (Mapping) and Step 1 are now multithreaded (e.g. up to 7x performance increase on a 6-Core 5600x).

Notes:

• Utilizes standalone version of PaddleOCR from https://github.com/timminator/PaddleOCR-Standalone
• Linux version requires glibc 2.35 or newer (can be checked by running ldd --version in a terminal)

Download Tips:

• Windows:
  • CPU version:
    VideOCR-CPU-v1.4.1-setup-x64.exe
  • GPU version:
    VideOCR-GPU-v1.4.1-CUDA-11.8-setup-x64.exe (Nvidia 10 Series graphics cards)
    VideOCR-GPU-v1.4.1-CUDA-12.9-setup-x64.exe (Nvidia 16 - 50 Series graphics cards)
• Linux:
  • CPU version:
    VideOCR-CPU-v1.4.1-Linux.7z
  • GPU version:
    VideOCR-GPU-v1.4.1-CUDA-11.8-Linux.7z (Nvidia 10 Series graphics cards)
    VideOCR-GPU-v1.4.1-CUDA-12.9-Linux.7z.001 (Nvidia 16 - 50 Series graphics cards)
    VideOCR-GPU-v1.4.1-CUDA-12.9-Linux.7z.002 (Nvidia 16 - 50 Series graphics cards)