$PATH

[Alqua]

I'm having different kind of issues on windows and in a linux vm. On windows, I think it is a $path problem, where in the code can I specify tesseract path? On linux: Error opening data file /usr/share/tesseract-ocr/4.00/tessdata/chi_sim.traineddata Please make sure the TESSDATA_PREFIX environment variable is set to your "tessdata" directory. Failed loading language 'chi_sim' Tesseract couldn't load any languages! Could not initialize tesseract.')

Also, I think PIL is deprecated now, is it? install should be set to Pillow

[Alqua]

ok I could make it function in windows but it makes an error:

File ".\build_subs.py", line 65, in gather_subs_tp if result['text'] == '': raise ValueError ValueError

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File ".\build_subs.py", line 184, in write_subs(subname, build_subs(sort_subs(gather_subs_tp(path, File ".\build_subs.py", line 76, in gather_subs_tp print('Did not run on: ', i) NameError: name 'i' is not defined

Does this mean it did not detect anything?

[Alqua]

Sorry for spamming, I ran it from the RGBimages folder and it generated okay result. Somehow, the cleaning from videoSubFinder was too much. Do you have any tips to improve the OCR for Chinese? Especially what options to change in VideoSubFinder for better result. Thanks for the codes! I'm happy I could make it work :)