The main purpose of this program is to provide functionality for extract hardcoded subtitles (hardsub) from video.
It provides two main features:
1) Autodetection of frames with hardcoded text (hardsub) on video with saving info about timing positions.
2) Generation of cleared from background text images, which allows with usage of OCR programs (like FineReader, Subtitle Edit, Google Drive) to generate complete subtitles with original text and timing.
For working of this program on Windows will be required "Microsoft Visual C++ Redistributable runtime libraries 2022":
https://support.microsoft.com/en-us/help/2977003/the-latest-supported-visual-c-downloads
Latest versions were built and tested on: Windows 10 x64, Ubuntu 20.04.5 LTS, openSUSE Leap 15.4, Arch Linux (EndeavourOS Cassini Nova 03-2023)
For faster support in case of bug fixes please contact me in:
https://vk.com/skosnits
For donate:
https://sourceforge.net/projects/videosubfinder/donate
Features
- video text detection
- text extraction from video frames
Project Samples
License
GNU General Public License version 2.0 (GPLv2)Follow VideoSubFinder
User Reviews
-
does what it's supposed to, but if you have a newer gpu, ex. one from the recently released rtx 5xxx series, it won't use it at all due to outdated cuda support (5xxx requires at least cuda 12.8 to function, which came out in 2025. at the time of writing this review the program was last updated in 2023), so it'll be using cpu only. that naturally will take a long time (ex. it'll takes over half an hour to process a 20 minute video for me).
-
Unfortunately it didn't extract anything from my video: strange... But maybe it is due to this specific video, and it will run with another one ...
-
awsome app, really hope to reduce the GPU needed
-
thank you for this amazing project, really helped me a lot. i have just one suggestion, maybe it could play a sound when a job is finished. like when the search is over and the clear text creation is over.Reply from VideoSubFinderPosted 2023-04-22
Hello, it is already supported) There is switch "Playback Sound On Task Finished" in Setting panel in the left side at the end of first group of settings. Also you can replace 'finished.wav' to some one else. -
UX could be a bit better, but it gets the job done! It also has a CLI mode which let's me integrate it into python scripts.