This release adds a lot of new features and improvements.
- The main highlight is the newly added support for PaddleOCR 3.x.x with greatly improved OCR capabilities in more than 40 languages,
including English, Chinese, Japanese, French, Spanish, Portuguese, Russian, Korean, etc.
Further highlights
- Add support for videos with variable frame rate
- Add support for videos with a start time offset
- Add Dual Zone OCR support
- Adds a post processing step to split wrongfully merged words
- Deprecated parameters similar image threshold and similar pixel threshold in favor of SSIM threshold. This new parameter enables speed improvements of over 500% for certain videos. More info about it can be found in the parameters section.
- Adds Taskbar progress indication for Windows
- Adds the ability to send notifications if the OCR process finished
- Add subtitle position parameter
- Add minimum subtitle duration parameter
- Adds an About Tab
Fixes:
- Fix sub sorting behaviour if there are multiple lines
- Fix video box not correctly scaling on Linux
- Disables angle classification by default
- Sets a unique app identifier
Notes:
- Utilizes standalone version of PaddleOCR from https://github.com/timminator/PaddleOCR-Standalone
- The GPU version requires an Nvidia graphics card (10 Series or newer) and driver version 522.25 (Linux: 520.56.06) or higher!
- Nvidia 50 Series is currently not [yet] supported!
- Linux version requires glibc 2.35 or newer (can be checked by running
ldd --versionin a terminal) - This release deprecates the old CLI in favor of CLI SA
- Windows releases were updated two days after the initial v1.3.0 release to fix a missing dependency on systems that did not have the Visual C++ Redistributable Packages for Visual Studio 2013 installed.