gnu: Add tesseract-ocr-tessdata-fast.

* gnu/packages/ocr.scm (tesseract-ocr-tessdata-fast): New variable.
This commit is contained in:
Maxim Cournoyer 2022-08-11 22:59:45 -04:00
parent ecc2587f1f
commit a6b6b0e89e
No known key found for this signature in database
GPG key ID: 1260E46482E63562

View file

@ -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")