tesstrain

tesstrain copied to clipboard

`make lists -j32` doesn't seem to be honoring the thread count. (Also happens when calling `make training -j32`)

3

Hi team, I'm training a model on some font with `START_MODEL=eng` and while the resulting .traineddata can correctly guess a lot of things with the font there are some which...

ipaqmaster

deu_latf wordfile

4

I tried to recognize some old Fraktur texts with deu_latf, but there are many words that are not recognized correctly, so I extracted the word list from deu_latf. This file...

Stond0cyborg

I tried to train Tesseract 5 with a new font in Thai but The BCER value keeps increasing. This is the detail Font : TH Sarabun New (200 samples) Base...

Kobayashi-UwU

How to train Chinese tradtional vertical in Tesseract 5?

1

This is the screenshot from jTessBoxEditor:  The provided [example training files](https://github.com/tesseract-ocr/tesstrain/blob/main/ocrd-testset.zip) in this repo seems building a whole line of image & text pairs, other than character-by-character. Then my...

fishfree

A question about missing dependency warnings when compiling and installing tesseract on centos using source code

1

When **centos** uses source code compilation to install tesseract, three dependent packages are missing. However, these three dependent packages have been installed and the versions fully meet the requirements. This...

bruceyu0114

Failed to read data/Assert failed

4

When trying to fine tune model, i get Failed to read data errors and then assert failed error ``` C:\Users\tobik\source\repos\tesstrain>make training MODEL_NAME=ocrd-testset START_MODEL=ces TESSDATA=C:\tessdata You are using make version: 4.4.1...

T0biasCZe

How to do incremental-training on tesseract-ocr?

5

I'm working with `tesseract-4.1.1` and trying to do training `(fine-tuning)` for this I have followed steps: 1. Downloaded `eng.traineddata` from `tessdata_best `and pasted it into `/usr/share/tesseract-ocr/4.00/tessdata`. 2. Then I've created...

zaryabRiasat

Trying to readme but I get: No box data found in 'data/foo-ground-truth/fontane_irrungen_1888_0258_008.box'....

2

Hi, I followed the tutorial, I extracted the content of `ocrd-testset.zip` in `./data/foo-ground-truth`, but when I run: > make training I get the following output: ``` (python) manuelarte@maclaptop tesstrain %...

manuelarte

Finetuning indic langauge models on word level?

1

If i have a dataset for which the model is not performing well. The dataset is on word level then can i train the tesseract model on the same dataset.

Souravakb24

I am actually working on training Grantha script. What I figured out is that both Tamil and Malayalam have almost same characters and formatting as that of Grantha. So, I...

Amricreate