This branch is 12 commits behind tesseract-ocr/tessdata:main.

Name	Name	Last commit message	Last commit date
Latest commit zdenop Merge pull request tesseract-ocr#99 from stweil/master May 10, 2018 590567f · May 10, 2018 History 33 Commits
script	script	Add scripts from tessdata_best (converted to fast integer models)	May 10, 2018
COPYING	COPYING	add license info	Aug 3, 2015
README.md	README.md	Fix typo in README.md	Apr 17, 2018
afr.traineddata	afr.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
amh.traineddata	amh.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
ara.traineddata	ara.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
asm.traineddata	asm.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
aze.traineddata	aze.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
aze_cyrl.traineddata	aze_cyrl.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
bel.traineddata	bel.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
ben.traineddata	ben.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
bod.traineddata	bod.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
bos.traineddata	bos.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
bre.traineddata	bre.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
bul.traineddata	bul.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
cat.traineddata	cat.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
ceb.traineddata	ceb.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
ces.traineddata	ces.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
chi_sim.traineddata	chi_sim.traineddata	Update traineddata LSTM model with best model converted to integer	May 10, 2018
chi_sim_vert.traineddata	chi_sim_vert.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
chi_tra.traineddata	chi_tra.traineddata	Update traineddata LSTM model with best model converted to integer	May 10, 2018
chi_tra_vert.traineddata	chi_tra_vert.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
chr.traineddata	chr.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
cos.traineddata	cos.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
cym.traineddata	cym.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
dan.traineddata	dan.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
dan_frak.traineddata	dan_frak.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
deu.traineddata	deu.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
deu_frak.traineddata	deu_frak.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
div.traineddata	div.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
dzo.traineddata	dzo.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
ell.traineddata	ell.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
eng.traineddata	eng.traineddata	Remove cube components from traineddata and update version component	May 10, 2018
enm.traineddata	enm.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
epo.traineddata	epo.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
equ.traineddata	equ.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
est.traineddata	est.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
eus.traineddata	eus.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
fao.traineddata	fao.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
fas.traineddata	fas.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
fil.traineddata	fil.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
fin.traineddata	fin.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
fra.traineddata	fra.traineddata	Remove cube components from traineddata and update version component	May 10, 2018
frk.traineddata	frk.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
frm.traineddata	frm.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
fry.traineddata	fry.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
gla.traineddata	gla.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
gle.traineddata	gle.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
glg.traineddata	glg.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
grc.traineddata	grc.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
guj.traineddata	guj.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
hat.traineddata	hat.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
heb.traineddata	heb.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
hin.traineddata	hin.traineddata	Only int best model for hin, san, mar, nep, tel and kan	Mar 22, 2018
hrv.traineddata	hrv.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
hun.traineddata	hun.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
hye.traineddata	hye.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
iku.traineddata	iku.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
ind.traineddata	ind.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
isl.traineddata	isl.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
ita.traineddata	ita.traineddata	Remove cube components from traineddata and update version component	May 10, 2018
ita_old.traineddata	ita_old.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
jav.traineddata	jav.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
jpn.traineddata	jpn.traineddata	Update traineddata LSTM model with best model converted to integer	May 10, 2018
jpn_vert.traineddata	jpn_vert.traineddata	Remove parameter textord_tabfind_vertical_horizontal_mix	Mar 29, 2018
kan.traineddata	kan.traineddata	Only int best model for hin, san, mar, nep, tel and kan	Mar 22, 2018
kat.traineddata	kat.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
kat_old.traineddata	kat_old.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
kaz.traineddata	kaz.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
khm.traineddata	khm.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
kir.traineddata	kir.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
kor.traineddata	kor.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
kor_vert.traineddata	kor_vert.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
kur.traineddata	kur.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
kur_ara.traineddata	kur_ara.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
lao.traineddata	lao.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
lat.traineddata	lat.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
lav.traineddata	lav.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
lit.traineddata	lit.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
ltz.traineddata	ltz.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
mal.traineddata	mal.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
mar.traineddata	mar.traineddata	Only int best model for hin, san, mar, nep, tel and kan	Mar 22, 2018
mkd.traineddata	mkd.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
mlt.traineddata	mlt.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
mon.traineddata	mon.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
mri.traineddata	mri.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
msa.traineddata	msa.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
mya.traineddata	mya.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
nep.traineddata	nep.traineddata	Only int best model for hin, san, mar, nep, tel and kan	Mar 22, 2018
nld.traineddata	nld.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
nor.traineddata	nor.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
oci.traineddata	oci.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
ori.traineddata	ori.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
osd.traineddata	osd.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
pan.traineddata	pan.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
pol.traineddata	pol.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
por.traineddata	por.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
pus.traineddata	pus.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
que.traineddata	que.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
ron.traineddata	ron.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
rus.traineddata	rus.traineddata	Remove cube components from traineddata and update version component	May 10, 2018
san.traineddata	san.traineddata	Only int best model for hin, san, mar, nep, tel and kan	Mar 22, 2018
sin.traineddata	sin.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
slk.traineddata	slk.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
slk_frak.traineddata	slk_frak.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
slv.traineddata	slv.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
snd.traineddata	snd.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
spa.traineddata	spa.traineddata	Remove cube components from traineddata and update version component	May 10, 2018
spa_old.traineddata	spa_old.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
sqi.traineddata	sqi.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
srp.traineddata	srp.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
srp_latn.traineddata	srp_latn.traineddata	Update LSTM Models to integerized tessdata_best for files < 25mb	Mar 22, 2018
sun.traineddata	sun.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
swa.traineddata	swa.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
swe.traineddata	swe.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
syr.traineddata	syr.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
tam.traineddata	tam.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
tat.traineddata	tat.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
tel.traineddata	tel.traineddata	Only int best model for hin, san, mar, nep, tel and kan	Mar 22, 2018
tgk.traineddata	tgk.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
tgl.traineddata	tgl.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
tha.traineddata	tha.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
tir.traineddata	tir.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
ton.traineddata	ton.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
tur.traineddata	tur.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
uig.traineddata	uig.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
ukr.traineddata	ukr.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
urd.traineddata	urd.traineddata	remove legacy model from indic and arabic script languages	Mar 22, 2018
uzb.traineddata	uzb.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
uzb_cyrl.traineddata	uzb_cyrl.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
vie.traineddata	vie.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
yid.traineddata	yid.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018
yor.traineddata	yor.traineddata	Update LSTM Models to integerized tessdata_best for files<25mb	Mar 22, 2018

Repository files navigation

tessdata

These language data files only work with Tesseract 4.0.0. They are based on the sources in tesseract-ocr/langdata on GitHub. (still to be updated for 4.0.0 - 20180322)

These have models for legacy tesseract engine (--oem 0) as well as the new LSTM neural net based engine (--oem 1).

The LSTM models (--oem 1) in these files have been updated to the integerized versions of tessdata_best on GitHub. So, they should be faster but probably a little less accurate than tessdata_best.

tessdata_fast on GitHub provides an alternate set of integerized LSTM models which have been built with a smaller network. tessdata_fast files are the ones packaged for Debian and Ubuntu.

The legacy tesseract models (--oem 0) have been removed for Indic and Arabic script language files.