'\" t
.\"     Title: combine_tessdata
.\"    Author: [see the "AUTHOR" section]
.\" Generator: DocBook XSL Stylesheets v1.79.1 <http://docbook.sf.net/>
.\"      Date: 01/21/2019
.\"    Manual: \ \&
.\"    Source: \ \&
.\"  Language: English
.\"
.TH "COMBINE_TESSDATA" "1" "01/21/2019" "\ \&" "\ \&"
.\" -----------------------------------------------------------------
.\" * Define some portability stuff
.\" -----------------------------------------------------------------
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.\" http://bugs.debian.org/507673
.\" http://lists.gnu.org/archive/html/groff/2009-02/msg00013.html
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\" -----------------------------------------------------------------
.\" * set default formatting
.\" -----------------------------------------------------------------
.\" disable hyphenation
.nh
.\" disable justification (adjust text to left margin only)
.ad l
.\" -----------------------------------------------------------------
.\" * MAIN CONTENT STARTS HERE *
.\" -----------------------------------------------------------------
.SH "NAME"
combine_tessdata \- combine/extract/overwrite/list/compact Tesseract data
.SH "SYNOPSIS"
.sp
\fBcombine_tessdata\fR [\fIOPTION\fR] \fIFILE\fR\&...
.SH "DESCRIPTION"
.sp
combine_tessdata(1) is the main program to combine/extract/overwrite/list/compact tessdata components in [lang]\&.traineddata files\&.
.sp
To combine all the individual tessdata components (unicharset, DAWGs, classifier templates, ambiguities, language configs) located at, say, /home/$USER/temp/eng\&.* run:
.sp
.if n \{\
.RS 4
.\}
.nf
combine_tessdata /home/$USER/temp/eng\&.
.fi
.if n \{\
.RE
.\}
.sp
The result will be a combined tessdata file /home/$USER/temp/eng\&.traineddata
.sp
Specify option \-e if you would like to extract individual components from a combined traineddata file\&. For example, to extract language config file and the unicharset from tessdata/eng\&.traineddata run:
.sp
.if n \{\
.RS 4
.\}
.nf
combine_tessdata \-e tessdata/eng\&.traineddata \e
  /home/$USER/temp/eng\&.config /home/$USER/temp/eng\&.unicharset
.fi
.if n \{\
.RE
.\}
.sp
The desired config file and unicharset will be written to /home/$USER/temp/eng\&.config /home/$USER/temp/eng\&.unicharset
.sp
Specify option \-o to overwrite individual components of the given [lang]\&.traineddata file\&. For example, to overwrite language config and unichar ambiguities files in tessdata/eng\&.traineddata use:
.sp
.if n \{\
.RS 4
.\}
.nf
combine_tessdata \-o tessdata/eng\&.traineddata \e
  /home/$USER/temp/eng\&.config /home/$USER/temp/eng\&.unicharambigs
.fi
.if n \{\
.RE
.\}
.sp
As a result, tessdata/eng\&.traineddata will contain the new language config and unichar ambigs, plus all the original DAWGs, classifier templates, etc\&.
.sp
Note: the file names of the files to extract to and to overwrite from should have the appropriate file suffixes (extensions) indicating their tessdata component type (\&.unicharset for the unicharset, \&.unicharambigs for unichar ambigs, etc)\&. See k*FileSuffix variable in ccutil/tessdatamanager\&.h\&.
.sp
Specify option \-u to unpack all the components to the specified path:
.sp
.if n \{\
.RS 4
.\}
.nf
combine_tessdata \-u tessdata/eng\&.traineddata /home/$USER/temp/eng\&.
.fi
.if n \{\
.RE
.\}
.sp
This will create /home/$USER/temp/eng\&.* files with individual tessdata components from tessdata/eng\&.traineddata\&.
.SH "OPTIONS"
.sp
\fB\-c\fR \fI\&.traineddata\fR \fIFILE\fR\&...: Compacts the LSTM component in the \&.traineddata file to int\&.
.sp
\fB\-d\fR \fI\&.traineddata\fR \fIFILE\fR\&...: Lists directory of components from the \&.traineddata file\&.
.sp
\fB\-e\fR \fI\&.traineddata\fR \fIFILE\fR\&...: Extracts the specified components from the \&.traineddata file
.sp
\fB\-o\fR \fI\&.traineddata\fR \fIFILE\fR\&...: Overwrites the specified components of the \&.traineddata file with those provided on the command line\&.
.sp
\fB\-u\fR \fI\&.traineddata\fR \fIPATHPREFIX\fR Unpacks the \&.traineddata using the provided prefix\&.
.SH "CAVEATS"
.sp
\fIPrefix\fR refers to the full file prefix, including period (\&.)
.SH "COMPONENTS"
.sp
The components in a Tesseract lang\&.traineddata file as of Tesseract 4\&.0 are briefly described below; For more information on many of these files, see \m[blue]\fBhttps://github\&.com/tesseract\-ocr/tesseract/wiki/TrainingTesseract\fR\m[] and \m[blue]\fBhttps://github\&.com/tesseract\-ocr/tesseract/wiki/TrainingTesseract\-4\&.00\fR\m[]
.PP
lang\&.config
.RS 4
(Optional) Language\-specific overrides to default config variables\&. For 4\&.0 traineddata files, lang\&.config provides control parameters which can affect layout analysis, and sub\-languages\&.
.RE
.PP
lang\&.unicharset
.RS 4
(Required \- 3\&.0x legacy tesseract) The list of symbols that Tesseract recognizes, with properties\&. See unicharset(5)\&.
.RE
.PP
lang\&.unicharambigs
.RS 4
(Optional \- 3\&.0x legacy tesseract) This file contains information on pairs of recognized symbols which are often confused\&. For example,
\fIrn\fR
and
\fIm\fR\&.
.RE
.PP
lang\&.inttemp
.RS 4
(Required \- 3\&.0x legacy tesseract) Character shape templates for each unichar\&. Produced by mftraining(1)\&.
.RE
.PP
lang\&.pffmtable
.RS 4
(Required \- 3\&.0x legacy tesseract) The number of features expected for each unichar\&. Produced by mftraining(1) from
\fB\&.tr\fR
files\&.
.RE
.PP
lang\&.normproto
.RS 4
(Required \- 3\&.0x legacy tesseract) Character normalization prototypes generated by cntraining(1) from
\fB\&.tr\fR
files\&.
.RE
.PP
lang\&.punc\-dawg
.RS 4
(Optional \- 3\&.0x legacy tesseract) A dawg made from punctuation patterns found around words\&. The "word" part is replaced by a single space\&.
.RE
.PP
lang\&.word\-dawg
.RS 4
(Optional \- 3\&.0x legacy tesseract) A dawg made from dictionary words from the language\&.
.RE
.PP
lang\&.number\-dawg
.RS 4
(Optional \- 3\&.0x legacy tesseract) A dawg made from tokens which originally contained digits\&. Each digit is replaced by a space character\&.
.RE
.PP
lang\&.freq\-dawg
.RS 4
(Optional \- 3\&.0x legacy tesseract) A dawg made from the most frequent words which would have gone into word\-dawg\&.
.RE
.PP
lang\&.fixed\-length\-dawgs
.RS 4
(Optional \- 3\&.0x legacy tesseract) Several dawgs of different fixed lengths \(em useful for languages like Chinese\&.
.RE
.PP
lang\&.shapetable
.RS 4
(Optional \- 3\&.0x legacy tesseract) When present, a shapetable is an extra layer between the character classifier and the word recognizer that allows the character classifier to return a collection of unichar ids and fonts instead of a single unichar\-id and font\&.
.RE
.PP
lang\&.bigram\-dawg
.RS 4
(Optional \- 3\&.0x legacy tesseract) A dawg of word bigrams where the words are separated by a space and each digit is replaced by a
\fI?\fR\&.
.RE
.PP
lang\&.unambig\-dawg
.RS 4
(Optional \- 3\&.0x legacy tesseract) \&.
.RE
.PP
lang\&.params\-model
.RS 4
(Optional \- 3\&.0x legacy tesseract) \&.
.RE
.PP
lang\&.lstm
.RS 4
(Required \- 4\&.0 LSTM) Neural net trained recognition model generated by lstmtraining\&.
.RE
.PP
lang\&.lstm\-punc\-dawg
.RS 4
(Optional \- 4\&.0 LSTM) A dawg made from punctuation patterns found around words\&. The "word" part is replaced by a single space\&. Uses lang\&.lstm\-unicharset\&.
.RE
.PP
lang\&.lstm\-word\-dawg
.RS 4
(Optional \- 4\&.0 LSTM) A dawg made from dictionary words from the language\&. Uses lang\&.lstm\-unicharset\&.
.RE
.PP
lang\&.lstm\-number\-dawg
.RS 4
(Optional \- 4\&.0 LSTM) A dawg made from tokens which originally contained digits\&. Each digit is replaced by a space character\&. Uses lang\&.lstm\-unicharset\&.
.RE
.PP
lang\&.lstm\-unicharset
.RS 4
(Required \- 4\&.0 LSTM) The unicode character set that Tesseract recognizes, with properties\&. Same unicharset must be used to train the LSTM and build the lstm\-*\-dawgs files\&.
.RE
.PP
lang\&.lstm\-recoder
.RS 4
(Required \- 4\&.0 LSTM) Unicharcompress, aka the recoder, which maps the unicharset further to the codes actually used by the neural network recognizer\&. This is created as part of the starter traineddata by combine_lang_model\&.
.RE
.PP
lang\&.version
.RS 4
(Optional) Version string for the traineddata file\&. First appeared in version 4\&.0 of Tesseract\&. Old version of traineddata files will report Version string:Pre\-4\&.0\&.0\&. 4\&.0 version of traineddata files may include the network spec used for LSTM training as part of version string\&.
.RE
.SH "HISTORY"
.sp
combine_tessdata(1) first appeared in version 3\&.00 of Tesseract
.SH "SEE ALSO"
.sp
tesseract(1), wordlist2dawg(1), cntraining(1), mftraining(1), unicharset(5), unicharambigs(5)
.SH "COPYING"
.sp
Copyright (C) 2009, Google Inc\&. Licensed under the Apache License, Version 2\&.0
.SH "AUTHOR"
.sp
The Tesseract OCR engine was written by Ray Smith and his research groups at Hewlett Packard (1985\-1995) and Google (2006\-present)\&.