From 52742e9a60458aa0080ad0021594b0ee8aaa135a Mon Sep 17 00:00:00 2001 From: Stefan Weil Date: Mon, 14 Aug 2023 21:11:49 +0200 Subject: [PATCH] Add OCR models Fraktur and Latin for Tesseract Both are not language specific, but support historic and current scripts used by many European languages. Signed-off-by: Stefan Weil --- public/langs.json | 6 ++++++ src/Engine/EngineBase.php | 2 ++ 2 files changed, 8 insertions(+) diff --git a/public/langs.json b/public/langs.json index a88b866..e418235 100644 --- a/public/langs.json +++ b/public/langs.json @@ -1,4 +1,10 @@ { + "Fraktur": { + "tesseract": "Fraktur" + }, + "Latin": { + "tesseract": "Latin" + }, "af": { "tesseract": "afr", "google": "af" diff --git a/src/Engine/EngineBase.php b/src/Engine/EngineBase.php index d9fa809..b1dacf1 100644 --- a/src/Engine/EngineBase.php +++ b/src/Engine/EngineBase.php @@ -36,6 +36,8 @@ abstract class EngineBase { /** @var string[] Additional localized names for non-standard language codes. */ public const LANG_NAMES = [ + 'Fraktur' => 'Fraktur script', + 'Latin' => 'Latin script', 'az-cyrl' => 'Azərbaycan (qədim yazı)', 'bali' => 'Balinese palm-leaf manuscripts 16th century', 'ben-print' => 'Bengali Printed Books +150 New',