[tesseract-ocr] Training Tesseract additional library install depend on broken packages

I have a problem following the Tesseract tutorial . The problem is the dependency package required by libpango1.0 can not be satisfied. The details are showed in a post

Re: [tesseract-ocr] Re: Fine tuning with existing box/tiff pairs in Tesseract 4.0

Thanks a lot for your help, everything worked, but now I have another problem. I generated .lstmf files with boxtrain.sh from six box-tiff pairs and everything was alright. I've added a few more pairs and now I get the "No block overlapping textline" error for almost every line in new box files.

Re: [tesseract-ocr] Tesseract 4 new Font

1. Which --oem are you using with tesseract 4, legacy engine or lstm? --oem 0 or --oem 1 2. Is Brazilian Portuguese very different from Portuguese? Please see the trainingtext and wordlists on https://github.com/tesseract-ocr/langdata/tree/master/por 3. Provide a sample image with it's ground

[tesseract-ocr] Tesseract 4 new Font

Hello! Guys I have tesseract 4 on Ubuntu 16.04. Running the tesseract with -l por (portuguese from Brazil) I don't have the good results. The image use other font than the trained data (I think). My question is. It's necessary to train tesseract again? I created the tif and box file with

[tesseract-ocr] Re: Tessnet2 path issue

Hello scMad! Did you find the solution to this??? On Friday, January 15, 2010 at 3:21:18 AM UTC+5, scMad wrote: > > I run windows 7 x64, and using tesseract and tessnet2 (I am using the > 32bit version tessnet2_32, as well as having the compiler set to > target x86). > > I receive an error on the