Hello, First of all let me start by saying that I greatly appreciate the amount of effort put into tesseract, how accurate it has become and the fact that is is free :-) I've read various topics about GPU support, and I understand that at some point OpenCL was planned, but didn't really go through? Since the newer versions use LSTM, I have to ask, are there any plans to offer CUDA support for training and/or evaluating (batch) documents? >From my limited understanding of LSTM I would have assumed that might make sense, although I also understand that the effort behind doing that would be huge. I am at a point where tesseract has gotten me good results with a variety of languages, but I can't use it in real-time applications because it seems to take on average 15 seconds per query, and I have been asked to reduce this to under a second. I apologise if this has been discussed before, I did try searching the forum first.
Regards, Alex -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/e280e222-4cb6-449b-9b67-7890021f39f9%40googlegroups.com.
