Let's start with the basics: The current leptonica version is 1.83.1 https://github.com/DanBloomberg/leptonica/releases The current tesseract version is 5.3.1 https://github.com/tesseract-ocr/tesseract/releases
Use the latest version if there is a problem. Nobody wants to waste time with (probably) already fixed issues. "4. We installed mar.traineddata ... -P tessdata_best" Why you pretend that tessdata is tessdata_best??? If you have a problem - stick to manual/documentation. Zdenko št 6. 7. 2023 o 19:50 Madhav Pandey <mad.develope...@gmail.com> napísal(a): > Hi Zdenop, I have provided all the information that you asked for in this > thread. Can you please help us here? > > If anything is missing, please let me know I can provide all the > information that you need. > > Thanks! > > On Thursday, 29 June 2023 at 18:50:01 UTC-6 Madhav Pandey wrote: > >> Hi Zdenop, >> >> Can you please provide some input here on why we might me getting this >> error? >> >> Thanks! >> >> On Wednesday, 28 June 2023 at 08:48:36 UTC-6 Madhav Pandey wrote: >> >>> Hi, >>> >>> Please find the detail below: >>> >>> 1. Dataset: It's available in marathi handwritten zip folder here >>> https://github.com/codeatpanorama/training-data/blob/main/marathi_handwritten_text.zip >>> 2. Log : Tesstrain.log file - >>> https://github.com/codeatpanorama/training-data/tree/main/logs >>> 3. Command Used: nohup make training MODEL_NAME=mar_hw START_MODEL=mar >>> TESSDATA=tessdata_best MAX_ITERATIONS=10000 LANG_TYPE=Indic > >>> plot/TESSTRAIN.LOG & >>> 4. We installed mar.traineddata using this command wget >>> https://github.com/tesseract-ocr/tessdata/raw/main/mar.traineddata >>> <https://github.com/tesseract-ocr/tessdata/raw/main/eng.traineddata> -P >>> tessdata_best >>> >>> This is out of tesseract version: >>> >>> tesseract 4.1.1 >>> >>> leptonica-1.79.0 >>> >>> libgif 5.1.4 : libjpeg 8d (libjpeg-turbo 2.0.3) : libpng 1.6.37 : >>> libtiff 4.1.0 : zlib 1.2.11 : libwebp 0.6.1 : libopenjp2 2.3.1 >>> >>> Found libarchive 3.4.0 zlib/1.2.11 liblzma/5.2.4 bz2lib/1.0.8 >>> liblz4/1.9.2 libzstd/1.4.4 >>> >>> Please help us unblock here. >>> >>> Also, When we omit the START_MODEL flag and solely provide the TESSDATA >>> path, which base model does Tesseract use for training? >>> >>> Thanks! >>> >> -- > 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 tesseract-ocr+unsubscr...@googlegroups.com. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/1ab011de-f527-431a-8c07-756c9955b01fn%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/1ab011de-f527-431a-8c07-756c9955b01fn%40googlegroups.com?utm_medium=email&utm_source=footer> > . > -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAJbzG8z790a%2BLMrf6CcaOacdVLxdfz8EkxO2-%2BovaPpsOuZs3w%40mail.gmail.com.
