GNU bug report logs - #57151
[PATCH 0/2] *** Add trained data models for Tesseract OCR ***

Previous Next

Full log

Message #8 received at 57151 <at> debbugs.gnu.org (full text, mbox):

From: Maxim Cournoyer <maxim.cournoyer <at> gmail.com>
To: 57151 <at> debbugs.gnu.org
Cc: Maxim Cournoyer <maxim.cournoyer <at> gmail.com>
Subject: [PATCH 1/2] gnu: Add tesseract-ocr-tessdata-fast.
Date: Fri, 12 Aug 2022 01:07:51 -0400

* gnu/packages/ocr.scm (tesseract-ocr-tessdata-fast): New variable.
---
 gnu/packages/ocr.scm | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/gnu/packages/ocr.scm b/gnu/packages/ocr.scm
index e28bd17668..e2c9f561cc 100644
--- a/gnu/packages/ocr.scm
+++ b/gnu/packages/ocr.scm
@@ -29,6 +29,7 @@ (define-module (gnu packages ocr)
   #:use-module (guix gexp)
   #:use-module (guix git-download)
   #:use-module (guix build-system cmake)
+  #:use-module (guix build-system copy)
   #:use-module (guix build-system gnu)
   #:use-module (guix build-system python)
   #:use-module (gnu packages)
@@ -74,6 +75,32 @@ (define-public ocrad
 it produces text in 8-bit or UTF-8 formats.")
     (license license:gpl3+)))
 
+(define-public tesseract-ocr-tessdata-fast
+  (package
+    (name "tesseract-ocr-tessdata-fast")
+    (version "4.1.0")
+    (source (origin
+              (method git-fetch)
+              (uri (git-reference
+                    (url "https://github.com/tesseract-ocr/tessdata_fast")
+                    (commit version)))
+              (file-name (git-file-name name version))
+              (sha256
+               (base32
+                "1m310cpb87xx8l8q7jy9fvzf6a0m8rm0dmjpbiwhc2mi6w4gn084"))))
+    (build-system copy-build-system)
+    (arguments (list #:install-plan #~'(("." "share/tesseract-ocr/tessdata"))
+                     #:phases #~(modify-phases %standard-phases
+                                  (add-after 'unpack 'delete-broken-links
+                                    (lambda _
+                                      (delete-file "configs")
+                                      (delete-file "pdf.ttf"))))))
+    (home-page "https://github.com/tesseract-ocr/tessdata_fast")
+    (synopsis "Fast integer versions of trained LSTM models")
+    (description "This repository contains fast integer versions of trained
+models for the Tesseract OCR Engine.")
+    (license license:asl2.0)))
+
 (define-public tesseract-ocr
   (package
     (name "tesseract-ocr")
-- 
2.36.1

Previous Next

GNU bug tracking system
Copyright (C) 1999 Darren O. Benham, 1997,2003 nCipher Corporation Ltd, 1994-97 Ian Jackson.