tdm17mn Posted January 1, 2016 Report Share Posted January 1, 2016 Hi guys, I have some Japanese language .sup files that I need to be able to copy and paste the text from, but I don't know how to convert the images from within the file to text? Is OCR my only option? It seems like OCR is impossible for Japanese files (didn't work well the first time I tried it years ago...) Is there any other way? Thank you very much. Link to comment Share on other sites More sharing options...
JohnFlower Posted January 1, 2016 Report Share Posted January 1, 2016 Try tesseract. It's in Subtitle Edit. If that fails then yeah, you're out of luck. Link to comment Share on other sites More sharing options...
Hark0n Posted January 1, 2016 Report Share Posted January 1, 2016 1 hour ago, JohnFlower said: Try tesseract. It's in Subtitle Edit. If that fails then yeah, you're out of luck. ^ This. Tesseract offers quite a few language options and works decant - there is a notable amount of errors, but any OCR process does have them. You will still need to check the script to make sure it is correct. Alternatively, it is possible to extract images from subs (tool like BDSup2Sub can do that) and run through any general OCR tool (like ABBYY FineReader) and add the resulting text into script. A bit different option would be to search for already OCRed or transcribed subs. Japanese subs for some anime are available at kitsunekko.net and some releases (usually from Chinese groups) at www.nyaa.se might have them in text format as well. Link to comment Share on other sites More sharing options...
kojiroryuga Posted January 17, 2016 Report Share Posted January 17, 2016 try http://download.videohelp.com/DVDSubEdit/ i use it to ripp subtitles from dvd and blu-ray, it have an automatic OCR you just have to read a second time to verify minors errors Link to comment Share on other sites More sharing options...
Recommended Posts
Please sign in to comment
You will be able to leave a comment after signing in
Sign In Now