tesseract-ocr/tesstrain issues and pull requests

#343 - Make last checkpoint also precious

Pull Request - State: closed - Opened by stweil over 1 year ago - 2 comments

#341 - Running Tesseract 5 training and how I solved the issues I found

Issue - State: open - Opened by mvfpoa over 1 year ago - 1 comment
Labels: stale

#340 - Can't encode transcription

Issue - State: open - Opened by zhoub over 1 year ago - 2 comments
Labels: stale

#339 - How does one turn (.tif, .gt.txt, .box) into (.lstmf)

Issue - State: closed - Opened by Turbine1991 over 1 year ago - 1 comment

#338 - Bad box coordinates in boxfile string!

Issue - State: open - Opened by khashashin over 1 year ago - 7 comments
Labels: stale

#337 - Encoding of string failed!

Issue - State: open - Opened by EurekaChen over 1 year ago - 1 comment

#336 - The box file is overwritten in training process

Issue - State: open - Opened by vishakraj25 over 1 year ago - 5 comments

#335 - Ground truth: spaces before and after text?

Issue - State: open - Opened by jbarth-ubhd over 1 year ago - 6 comments
Labels: stale

#334 - generate_line_box.py fails with empty .txt

Issue - State: closed - Opened by jbarth-ubhd over 1 year ago - 2 comments

#333 - FINETUNE_TYPE gone?

Issue - State: closed - Opened by jbarth-ubhd over 1 year ago - 1 comment

#332 - Is it possible to train a model for multiple types of sources?

Issue - State: open - Opened by gabriel-fsa over 1 year ago - 7 comments
Labels: stale

#331 - make trained model from checkpoint files

Issue - State: open - Opened by z160896 over 1 year ago - 1 comment
Labels: stale

#330 - Compiling error

Issue - State: closed - Opened by z160896 over 1 year ago - 1 comment

#329 - How to train new language

Issue - State: closed - Opened by Erdene-Ochir0417 over 1 year ago - 1 comment

#328 - FileNotFoundError: [Errno 2] No such file or directory: 'data/namaq/all-lstmf'

Issue - State: closed - Opened by ShahadAlkhalifa over 1 year ago - 14 comments

#326 - training fail again and again

Issue - State: open - Opened by Ham714 over 1 year ago - 5 comments
Labels: stale

#325 - Error while training on sample data.

Issue - State: closed - Opened by tevzselcan over 1 year ago - 5 comments

#324 - Fine-tune the english model

Issue - State: closed - Opened by gabriel-fsa almost 2 years ago - 2 comments

#323 - failure training

Issue - State: closed - Opened by ccampisano almost 2 years ago - 19 comments

#322 - Question: Training seems to work fine, but using traineddata file produces garbage

Issue - State: open - Opened by lzhaxi almost 2 years ago - 3 comments
Labels: stale

#321 - make "liblept.la install-recursive leptonica.built" error

Issue - State: closed - Opened by weiailuxueqi almost 2 years ago - 2 comments

#320 - support training from .raw.png

Pull Request - State: closed - Opened by bertsky almost 2 years ago - 3 comments

#319 - Add CodeQL workflow for GitHub code scanning

Pull Request - State: closed - Opened by lgtm-com[bot] almost 2 years ago

#318 - prevent checkpoint file from being deleted when "make training" is interrupted

Pull Request - State: closed - Opened by brakhane almost 2 years ago - 2 comments

#317 - About configuration for arabic handwriting traineddata, please?

Issue - State: open - Opened by Alhar6i almost 2 years ago - 3 comments
Labels: question, stale

#316 - Incorrect/outdated documentation in README.md

Issue - State: open - Opened by pratheesh-prakash almost 2 years ago - 4 comments
Labels: enhancement

#315 - training tesseract for persian (fas) language

Issue - State: closed - Opened by m-kafiyan almost 2 years ago - 1 comment
Labels: stale

#314 - Line images max characters/max width

Issue - State: closed - Opened by naourass about 2 years ago - 1 comment
Labels: stale

#313 - ./plot/plot_cer.sh is missing!

Issue - State: closed - Opened by MeilyOeng about 2 years ago - 3 comments
Labels: stale

#312 - how to prepare the data for new tessdata images in khmer lang

Issue - State: closed - Opened by mengleang-ngoun about 2 years ago - 2 comments
Labels: stale

#311 - number of MAX_ITERATIONS

Issue - State: closed - Opened by whisere about 2 years ago - 4 comments
Labels: question, stale

#310 - Missing config in new created traineddata

Issue - State: open - Opened by MPQC over 2 years ago - 1 comment
Labels: enhancement

#309 - Migrate Python code to a dedicated package

Pull Request - State: closed - Opened by stefan6419846 over 2 years ago - 16 comments

#308 - Python package for tesstrain.py

Issue - State: closed - Opened by stefan6419846 over 2 years ago
Labels: enhancement

#307 - Migrating from tesstrain.sh

Issue - State: closed - Opened by stefan6419846 over 2 years ago - 5 comments
Labels: stale

#306 - Question : unicharset_extractor error. How can i solved it ?

Issue - State: closed - Opened by Iaurkano64 over 2 years ago - 3 comments

#305 - Training for fonts?

Issue - State: closed - Opened by orsondmc over 2 years ago - 3 comments
Labels: question, stale

#304 - Failed to read boxes

Issue - State: open - Opened by NoxideLive over 2 years ago - 6 comments
Labels: bug

#303 - plot_cer_validation

Issue - State: closed - Opened by whisere over 2 years ago - 20 comments

#302 - [Question] How to generate tif line images from tif pages / How to train with no specified language?

Issue - State: closed - Opened by Marco-Parente over 2 years ago - 2 comments
Labels: stale

#301 - RTL language training issue

Issue - State: closed - Opened by sameearif88 over 2 years ago

#300 - how to prepare the data for new tessdata images in arabic lang

Issue - State: closed - Opened by Mahmuod1 over 2 years ago - 1 comment
Labels: stale

#299 - make deletes checkpoint file on crash/interrupt

Issue - State: closed - Opened by dantmnf over 2 years ago - 3 comments
Labels: stale

#298 - Need to call text2image unique "--fontconfig_tmpdir" when multi-threaded

Issue - State: closed - Opened by james-evy over 2 years ago - 1 comment
Labels: stale

#297 - Why do we have tesstrain.py in this repo?

Issue - State: closed - Opened by wrznr over 2 years ago - 2 comments
Labels: help wanted, stale

#296 - tesstrain.py: UnicodeEncodeError for font names

Issue - State: closed - Opened by Shreeshrii over 2 years ago - 2 comments
Labels: stale

#295 - lstmtraining: command not found

Issue - State: closed - Opened by TheFattestTony over 2 years ago - 14 comments

#294 - training failed for persian language with new font

Issue - State: open - Opened by mohsenomidi over 2 years ago - 22 comments

#293 - Question - [Generating Traindata]

Issue - State: closed - Opened by mohsenomidi almost 3 years ago - 2 comments

#292 - Documenting the bug and isses trying to rebuild eng.traineddata from scratch form langdata_lstm

Issue - State: closed - Opened by james-evy almost 3 years ago - 18 comments
Labels: off-topic, stale

#291 - Trained Arabic model results are reversed

Issue - State: closed - Opened by ShroukMansour almost 3 years ago - 3 comments
Labels: question, stale

#290 - Question: What is a line image?

Issue - State: closed - Opened by NeilduToit13 almost 3 years ago - 4 comments
Labels: question

#289 - [tesseract-ocr/tesstrain#288] updating urls to access raw content on github.com

Pull Request - State: closed - Opened by z-aliakseyeu almost 3 years ago - 2 comments
Labels: stale

#288 - Invalid github urls

Issue - State: closed - Opened by z-aliakseyeu almost 3 years ago - 2 comments
Labels: stale

#287 - LSTMF file are not getting generated for some part of dataset

Issue - State: closed - Opened by shirish100 almost 3 years ago - 3 comments
Labels: question, stale

#286 - an error while building

Issue - State: closed - Opened by jmu201621143028 almost 3 years ago - 2 comments

#285 - How to stop training?

Issue - State: closed - Opened by haideralipf almost 3 years ago - 1 comment

#284 - Regarding fine-tuned traindata model size

Issue - State: closed - Opened by nikhilcms almost 3 years ago - 3 comments
Labels: question

#283 - lstmeval not matching up with what I see when running Tesseract command line

Issue - State: closed - Opened by hartjac23 almost 3 years ago - 1 comment
Labels: duplicate

#282 - Training Seven Segment Display for OCR

Issue - State: closed - Opened by dpanic almost 3 years ago - 2 comments

#281 - Error In Training

Issue - State: closed - Opened by shirish100 about 3 years ago

#280 - Regarding the training data

Issue - State: closed - Opened by SreyaKambhatla about 3 years ago - 2 comments
Labels: stale

#279 - error during training ( make: * [data/foo/foo.traineddata] Error)

Issue - State: closed - Opened by nebiyebln about 3 years ago - 5 comments
Labels: stale

#278 - radical-stroke.txt location changed

Issue - State: closed - Opened by aquino-a about 3 years ago - 6 comments
Labels: stale

#277 - make training hung

Issue - State: closed - Opened by NeilduToit13 about 3 years ago - 3 comments
Labels: stale

#276 - Question on handwriting OCR

Issue - State: open - Opened by Archilegt about 3 years ago - 8 comments
Labels: question, pinned

#275 - After running the make training command, only the all-boxes file is created.

Issue - State: closed - Opened by ozlem-atiz about 3 years ago - 11 comments
Labels: question, stale

#274 - Guidance to improve speed.

Issue - State: closed - Opened by vijuc895 about 3 years ago - 1 comment

#273 - Does not create lstmf file: Compute CTC targets failed!

Issue - State: closed - Opened by townim-faisal about 3 years ago - 4 comments

#272 - Will training on images that tesseract already can OCR correctly help it OCR similar images but with different content ?

Issue - State: closed - Opened by AdnanCukur about 3 years ago - 3 comments
Labels: question, stale

GitHub / tesseract-ocr/tesstrain issues and pull requests