From dfe3ab30b8eba7ceba1fde3efaab1295c44aaaa6 Mon Sep 17 00:00:00 2001 From: Robert Sachunsky <38561704+bertsky@users.noreply.github.com> Date: Tue, 21 May 2024 17:25:23 +0200 Subject: [PATCH] recognize models: use _best instead of _fast (to prevent rare Tesseract crashes) --- ocrd_tesserocr/ocrd-tool.json | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/ocrd_tesserocr/ocrd-tool.json b/ocrd_tesserocr/ocrd-tool.json index 30f813d..baa29d3 100644 --- a/ocrd_tesserocr/ocrd-tool.json +++ b/ocrd_tesserocr/ocrd-tool.json @@ -210,7 +210,7 @@ "resource_locations": ["module"], "resources": [ { - "url": "https://ub-backup.bib.uni-mannheim.de/~stweil/ocrd-train/data/Fraktur_5000000/tessdata_fast/Fraktur_50000000.334_450937.traineddata", + "url": "https://ub-backup.bib.uni-mannheim.de/~stweil/ocrd-train/data/Fraktur_5000000/tessdata_best/Fraktur_50000000.334_450937.traineddata", "name": "Fraktur_GT4HistOCR.traineddata", "parameter_usage": "without-extension", "description": "Tesseract LSTM model trained on GT4HistOCR", @@ -231,56 +231,56 @@ "size": 3421140 }, { - "url": "https://github.com/tesseract-ocr/tessdata_fast/raw/main/equ.traineddata", + "url": "https://github.com/tesseract-ocr/tessdata_best/raw/main/equ.traineddata", "name": "equ.traineddata", "parameter_usage": "without-extension", "description": "Tesseract legacy model for mathematical equations", "size": 2251950 }, { - "url": "https://github.com/tesseract-ocr/tessdata_fast/raw/main/osd.traineddata", + "url": "https://github.com/tesseract-ocr/tessdata_best/raw/main/osd.traineddata", "name": "osd.traineddata", "parameter_usage": "without-extension", "description": "Tesseract legacy model for orientation and script detection", "size": 10562727 }, { - "url": "https://github.com/tesseract-ocr/tessdata_fast/raw/main/eng.traineddata", + "url": "https://github.com/tesseract-ocr/tessdata_best/raw/main/eng.traineddata", "name": "eng.traineddata", "parameter_usage": "without-extension", "description": "Tesseract LSTM model for contemporary (computer typesetting and offset printing) English", "size": 4113088 }, { - "url": "https://github.com/tesseract-ocr/tessdata_fast/raw/main/deu.traineddata", + "url": "https://github.com/tesseract-ocr/tessdata_best/raw/main/deu.traineddata", "name": "deu.traineddata", "parameter_usage": "without-extension", "description": "Tesseract LSTM model for contemporary (computer typesetting and offset printing) German", "size": 1525436 }, { - "url": "https://github.com/tesseract-ocr/tessdata_fast/raw/main/deu_latf.traineddata", + "url": "https://github.com/tesseract-ocr/tessdata_best/raw/main/deu_latf.traineddata", "name": "deu_latf.traineddata", "parameter_usage": "without-extension", "description": "Tesseract LSTM model for historical (Fraktur typesetting and letterpress printing) German", "size": 6423052 }, { - "url": "https://github.com/tesseract-ocr/tessdata_fast/raw/main/deu_latf.traineddata", + "url": "https://github.com/tesseract-ocr/tessdata_best/raw/main/deu_latf.traineddata", "name": "frk.traineddata", "parameter_usage": "without-extension", "description": "Tesseract LSTM model for historical German (deprecated, replaced by deu_latf)", "size": 6423052 }, { - "url": "https://github.com/tesseract-ocr/tessdata_fast/raw/main/script/Fraktur.traineddata", + "url": "https://github.com/tesseract-ocr/tessdata_best/raw/main/script/Fraktur.traineddata", "name": "Fraktur.traineddata", "parameter_usage": "without-extension", "description": "Tesseract LSTM model for historical Latin script with Fraktur typesetting", "size": 10915632 }, { - "url": "https://github.com/tesseract-ocr/tessdata_fast/raw/main/script/Latin.traineddata", + "url": "https://github.com/tesseract-ocr/tessdata_best/raw/main/script/Latin.traineddata", "name": "Latin.traineddata", "parameter_usage": "without-extension", "description": "Tesseract LSTM model for contemporary and historical Latin script",