sometimes it reads the number completely false unfortunately. I'm going to see if there is a youtube tutorial for tesseract 4 training. this google support kinda not it, it seems ...
Thanks. Shavkat Sultanov schrieb am Samstag, 10. Januar 2026 um 11:33:56 UTC+1: > I guess I'm going to try tesseract 4 then ? Maybe there is better > documentation for it. > > Shavkat Sultanov schrieb am Donnerstag, 8. Januar 2026 um 10:24:16 UTC+1: > >> please help. >> >> Shavkat Sultanov schrieb am Donnerstag, 8. Januar 2026 um 10:24:05 UTC+1: >> >>> >>> hello? >>> Shavkat Sultanov schrieb am Mittwoch, 7. Januar 2026 um 12:14:47 UTC+1: >>> >>>> Hi there, >>>> >>>> >>>> I asked a question before, that one got solved. >>>> >>>> I am further down the training process and I need help. >>>> >>>> when I try to run the training script (make training ...) the first >>>> time, it does a lot of stuff, namely making more files, that it is >>>> supposed >>>> to do, as per the user manual. >>>> >>>> but it is still failing and I do not know why, unfortunately. >>>> >>>> I ran it again, to produce the error again, it will not show making of >>>> all those .box-files and such. I am having trouble copying from the >>>> command >>>> line inteface aswell... . >>>> >>>> here is my command and it's output though, I hope you can help me with >>>> this: >>>> >>>> shavkat95@ubuntu:/mnt/tesstrain$ sudo make training RATIO_TRAIN=1.0 >>>> MODEL_NAME=gg_custom_1 DATA_DIR=./data >>>> GROUND_TRUTH_DIR=./data/gg_custom_1-ground-truth START_MODEL=eng >>>> MAX_ITERATIONS=500 TESSDATA=/mnt/tesseract/tessdata >>>> You are using make version: 4.3 >>>> >>>> lstmtraining \ >>>> --debug_interval 0 \ >>>> --traineddata ./data/gg_custom_1/gg_custom_1.traineddata \ >>>> --old_traineddata /mnt/tesseract/tessdata/eng.traineddata \ >>>> --continue_from ./data/eng/gg_custom_1.lstm \ >>>> --learning_rate 0.0001 \ >>>> --model_output ./data/gg_custom_1/checkpoints/gg_custom_1 \ >>>> --train_listfile ./data/gg_custom_1/list.train \ >>>> --eval_listfile ./data/gg_custom_1/list.eval \ >>>> --max_iterations 500 \ >>>> --target_error_rate 0.01 \ >>>> 2>&1 | tee -a ./data/gg_custom_1/training.log >>>> Loaded file ./data/eng/gg_custom_1.lstm, unpacking... >>>> Warning: LSTMTrainer deserialized an LSTMRecognizer! >>>> Code range changed from 111 to 111! >>>> Num (Extended) outputs,weights in Series: >>>> 1,36,0,1:1, 0 >>>> Num (Extended) outputs,weights in Series: >>>> C3,3:9, 0 >>>> Ft16:16, 160 >>>> Total weights = 160 >>>> [C3,3Ft16]:16, 160 >>>> Mp3,3:16, 0 >>>> TxyLfys64:64, 20736 >>>> Lfx96:96, 61824 >>>> RxLrx96:96, 74112 >>>> Lfx512:512, 1247232 >>>> Fc111:111, 56943 >>>> Total weights = 1461007 >>>> Previous null char=110 mapped to 110 >>>> Continuing from ./data/eng/gg_custom_1.lstm >>>> Failed to load list of eval filenames from ./data/gg_custom_1/list.eval >>>> Failed to load eval data from: ./data/gg_custom_1/list.eval >>>> >>>> lstmtraining \ >>>> --stop_training \ >>>> --continue_from ./data/gg_custom_1/checkpoints/gg_custom_1_checkpoint \ >>>> --traineddata ./data/gg_custom_1/gg_custom_1.traineddata \ >>>> --model_output data/gg_custom_1.traineddata >>>> Failed to read continue from: >>>> ./data/gg_custom_1/checkpoints/gg_custom_1_checkpoint >>>> make: *** [Makefile:325: data/gg_custom_1.traineddata] Error 1 >>>> >>>> >>>> >>>> Thanks in advance! >>>> >>>> >>>> Kind regards, >>>> Shavkat Sultanov >>>> >>>> -- 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 visit https://groups.google.com/d/msgid/tesseract-ocr/aa3ad77c-4eec-473a-a0e0-1bd2d4da4ab2n%40googlegroups.com.
