Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / tesseract-ocr/tessdata_best issues and pull requests

#82 - Tesseract

Issue - State: closed - Opened by DrShroom424 about 2 months ago
Labels: invalid

#81 - How does Tesseract OCR fuse results from multiple models?

Issue - State: open - Opened by yaofuzhou 7 months ago - 1 comment

#80 - Rename frk -> deu_latf (ISO 639-3, ISO 15924)

Pull Request - State: closed - Opened by stweil 7 months ago - 1 comment

#78 - Suggests adding `grc_hist.traineddata`

Pull Request - State: closed - Opened by sven-nm about 1 year ago - 2 comments

#77 - Still getting extra spacing in between characters for jpn

Issue - State: open - Opened by Latrolage about 1 year ago

#76 - Poor results combining scripts

Issue - State: open - Opened by simonante over 1 year ago

#75 - Added LSTM model for Akkadian

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

#74 - best and fast should have the same config file

Issue - State: open - Opened by amitdo over 1 year ago

#73 - Hebrew david font support

Issue - State: open - Opened by shimondoodkin over 1 year ago

#72 - `chi_tra` does not recognize vertical text as the doc says

Issue - State: open - Opened by Gowee over 1 year ago

#71 - convert eng training to h5 model

Issue - State: open - Opened by ehrenmann1977 over 2 years ago - 3 comments
Labels: enhancement

#70 - Invalid symlink makes tar fail

Issue - State: closed - Opened by Mek101 over 2 years ago - 3 comments
Labels: question

#69 - Using tessdata_best files leads to error

Issue - State: closed - Opened by qwertynik over 2 years ago - 5 comments

#68 - unclear/ambiguous language code notation

Issue - State: open - Opened by michaelkubina over 2 years ago - 10 comments
Labels: enhancement

#67 - Ara language is showing "empty page!!" on one laptop and gives the answer on another

Issue - State: closed - Opened by larawehbe over 2 years ago - 4 comments
Labels: question

#65 - Improved Tamil and Sinhala traineddata

Pull Request - State: open - Opened by Chaarangan about 3 years ago - 4 comments

#59 - Which language file should be downloaded?

Issue - State: closed - Opened by oasaleh about 3 years ago - 2 comments

#58 - finetune tesseract on 2 languages

Issue - State: open - Opened by mhrihab about 3 years ago - 1 comment

#57 - [ISSUE] (OSD) orientation script detection not supported using Tesseract best

Issue - State: closed - Opened by davidpraise45 about 3 years ago - 2 comments
Labels: question

#56 - Segment error (core dumped)

Issue - State: closed - Opened by MollyHoo over 3 years ago - 2 comments
Labels: question

#55 - CHI_SIM molde load error

Issue - State: closed - Opened by wunengbiao over 3 years ago - 1 comment

#54 - Tesseract can not detect @ sign in Turkish language

Issue - State: open - Opened by bagsergen about 4 years ago - 1 comment
Labels: bug

#53 - Performance post Fine-Tuning

Issue - State: open - Opened by rraina97 about 4 years ago

#52 - Fine Tuning

Issue - State: closed - Opened by rraina97 over 4 years ago - 1 comment

#51 - Portuguese trained data fails to recognize @

Issue - State: open - Opened by jgsmarques over 4 years ago - 3 comments
Labels: bug

#49 - eng.traineddata from tessdata_best on Android gives initialization error

Issue - State: closed - Opened by Kunal-git over 4 years ago - 1 comment

#48 - Can't use ita.traineddata

Issue - State: closed - Opened by Betacentury over 4 years ago - 2 comments

#47 - Update README

Pull Request - State: closed - Opened by yakryder over 4 years ago - 2 comments

#46 - Update README

Pull Request - State: closed - Opened by yakryder over 4 years ago

#45 - "§" symbol is not recognized in German language models

Issue - State: closed - Opened by Apolyxon over 4 years ago - 6 comments
Labels: duplicate

#44 - Not able to download the zip or clone this repo.

Issue - State: closed - Opened by aby005 over 4 years ago - 1 comment
Labels: question

#43 - Digit mixed up

Issue - State: closed - Opened by NiHoel almost 5 years ago - 1 comment

#42 - fra.traineddata corrupted ?

Issue - State: closed - Opened by japafrite almost 5 years ago - 3 comments
Labels: question

#40 - Tesseract fails to recognize % sign in Hungarian language texts

Issue - State: open - Opened by Googulator about 5 years ago - 8 comments
Labels: bug

#39 - Source of scripts/Fraktur etc.

Issue - State: closed - Opened by mikegerber over 5 years ago - 8 comments

#38 - Fail to load standalone number or some words in Vietnamese

Issue - State: closed - Opened by YuiyuD001 over 5 years ago - 1 comment

#37 - Fix extra intra-word spacing for several Asian languages (GitHub issue #991)

Pull Request - State: closed - Opened by stweil over 5 years ago - 1 comment

#36 - tessdata_best failed loading language

Issue - State: closed - Opened by AnandTiwari1997 over 5 years ago - 3 comments

#35 - Polytonic characters on Greek trained data files

Issue - State: open - Opened by kchrs almost 6 years ago

#34 - Wrong text recognition when there is a mix of numbers and characters

Issue - State: open - Opened by efollana-sistel almost 6 years ago - 1 comment

#33 - Improve documentation

Pull Request - State: closed - Opened by stweil almost 6 years ago - 2 comments

#32 - Telugu unicode ambiguities

Issue - State: open - Opened by 30atm about 6 years ago - 5 comments

#31 - request to add new fonts for Telugu language

Issue - State: closed - Opened by 30atm about 6 years ago - 2 comments

#30 - Failed loading language 'eng'

Issue - State: closed - Opened by kakadiyahardik about 6 years ago - 1 comment

#28 - Remove parameter textord_tabfind_vertical_horizontal_mix

Pull Request - State: closed - Opened by stweil over 6 years ago

#27 - Adding khmLimon.traineddata

Pull Request - State: closed - Opened by phyrumsk over 6 years ago - 20 comments

#26 - correct name kur_ara to kmr - Kurmanji (Latin script)

Pull Request - State: closed - Opened by Shreeshrii over 6 years ago - 2 comments

#25 - Fix config file for Korean, remove `tessedit_load_sublangs chi_tra`

Pull Request - State: closed - Opened by Shreeshrii over 6 years ago - 2 comments

#24 - old russian / church slavonic glyphs?

Issue - State: open - Opened by yurytch over 6 years ago - 13 comments
Labels: enhancement

#23 - Add kur with Arabic unicharset (similar to old tessdata)

Issue - State: open - Opened by Shreeshrii over 6 years ago - 3 comments

#22 - File Error Reporting: The Chi_Tra file is actually a Chi_Tra_vert file

Issue - State: open - Opened by mathshk20012001 over 6 years ago - 1 comment

#21 - Move trained data for scripts to new subdirectory

Pull Request - State: closed - Opened by stweil over 6 years ago

#19 - Add Devanagari config file to fix auto PSM issue #1273

Pull Request - State: closed - Opened by stweil over 6 years ago

#18 - can you recommend the best traineddata for numbers and latin letters

Issue - State: closed - Opened by JenyaKirmizaTripTop over 6 years ago - 4 comments

#17 - deu: Remove unwanted dependency

Pull Request - State: closed - Opened by stweil over 6 years ago - 12 comments

#16 - Add description regarding 'Script' traineddata

Pull Request - State: closed - Opened by Shreeshrii over 6 years ago - 2 comments

#15 - Fine tuning training for a mix language tessdata

Issue - State: closed - Opened by amitm02 over 6 years ago - 6 comments

#14 - jpn.traineddata often interprets large もs as るs

Issue - State: closed - Opened by wareya over 6 years ago - 1 comment

#13 - Failed loading language 'Armenian' and 'hye'

Issue - State: closed - Opened by axper almost 7 years ago - 4 comments

#12 - Wrong encoding of accented characters in grc.traineddata

Issue - State: closed - Opened by pharos-alexandria almost 7 years ago

#11 - confusing on results of ARABIC COMMA (u060C) for fas.traineddata

Issue - State: closed - Opened by hsen-dev almost 7 years ago - 31 comments

#10 - Lao.traineddata and lao.traineddata names conflict on macOS filesystem

Issue - State: closed - Opened by willfrey almost 7 years ago - 4 comments

#9 - Two different trained data files for greek language

Issue - State: closed - Opened by VasLem almost 7 years ago - 2 comments

#8 - crash when use tesseract 4 from cocoapod

Issue - State: closed - Opened by 0xhakawai almost 7 years ago - 4 comments

#7 - Eng traindata and tight text

Issue - State: closed - Opened by kalaspuffar almost 7 years ago - 2 comments

#6 - There are 2 traineddata for khmer language

Issue - State: closed - Opened by phyrumsk almost 7 years ago - 4 comments

#5 - Can improved san.traineddata be uploaded in this repo?

Issue - State: closed - Opened by Shreeshrii almost 7 years ago

#4 - Feedback Latin.traineddata

Issue - State: closed - Opened by TheSeiko about 7 years ago - 5 comments

#3 - Fix Config files to LSTM only for nep and mar

Pull Request - State: closed - Opened by Shreeshrii about 7 years ago

#2 - Fix config files - Tesseract/LSTM combiner to LSTM only

Pull Request - State: closed - Opened by Shreeshrii about 7 years ago - 1 comment

#1 - Improve GitHub integration

Pull Request - State: closed - Opened by stweil about 7 years ago - 4 comments