timminator/VideOCR v1.6.0 on GitHub

Highlights:

Adds support for the new PaddleOCR v3.7.0 version which improved accuracy for Chinese, English, Japanese and Latin languages. Other languages also profit from the improved detection model.
Adds option to save OCR detection/recognition images annotated with the detected boxes/text (currently limited to PaddleOCR), useful for reviewing or debugging OCR results
Adds Drag and Drop Support (Currently limited to Windows due to an upstream issue on Linux)
Adds option to disable frame stitching for better OCR accuracy
Adds Copy CLI command to clipboard feature
Adds option to reset settings back to default

Fixed a crash of the video preview of the GUI caused by a few select video files
Fixed a mistake in the available PaddleOCR language list in the GUI
Improved performance if a brightness threshold was applied
Quite a few optimizations were done to shrink down the GUI and CLI executable size

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