mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: add missing font download in the rapidocr artifacts (#2735)

Browse Source 
add font in the rapidocr downloads

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-12-08 12:44:53 +01:00
committed by GitHub
parent 609069d12c
commit edbabfcac2
1 changed files with 17 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
docling/models/rapid_ocr_model.py
View File

@@ -24,7 +24,7 @@ _log = logging.getLogger(__name__)
_ModelPathEngines = Literal["onnxruntime", "torch"] _ModelPathEngines = Literal["onnxruntime", "torch"]
_ModelPathTypes = Literal[ _ModelPathTypes = Literal[
"det_model_path", "cls_model_path", "rec_model_path", "rec_keys_path" "det_model_path", "cls_model_path", "rec_model_path", "rec_keys_path", "font_path"
] ]
@@ -58,6 +58,10 @@ class RapidOcrModel(BaseOcrModel):
"url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v2.0.7/paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_infer/ppocr_keys_v1.txt", "url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v2.0.7/paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_infer/ppocr_keys_v1.txt",
"path": "paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_infer/ppocr_keys_v1.txt", "path": "paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_infer/ppocr_keys_v1.txt",
}, },
"font_path": {
"url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.4.0/resources/fonts/FZYTK.TTF",
"path": "fonts/FZYTK.TTF",
},
}, },
"torch": { "torch": {
"det_model_path": { "det_model_path": {
@@ -76,6 +80,10 @@ class RapidOcrModel(BaseOcrModel):
"url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.4.0/paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_infer/ppocr_keys_v1.txt", "url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.4.0/paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_infer/ppocr_keys_v1.txt",
"path": "paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_infer/ppocr_keys_v1.txt", "path": "paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_infer/ppocr_keys_v1.txt",
}, },
"font_path": {
"url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.4.0/resources/fonts/FZYTK.TTF",
"path": "fonts/FZYTK.TTF",
},
}, },
} }
@@ -125,6 +133,7 @@ class RapidOcrModel(BaseOcrModel):
cls_model_path = self.options.cls_model_path cls_model_path = self.options.cls_model_path
rec_model_path = self.options.rec_model_path rec_model_path = self.options.rec_model_path
rec_keys_path = self.options.rec_keys_path rec_keys_path = self.options.rec_keys_path
font_path = self.options.font_path
if artifacts_path is not None: if artifacts_path is not None:
det_model_path = ( det_model_path = (
det_model_path det_model_path
@@ -150,12 +159,19 @@ class RapidOcrModel(BaseOcrModel):
/ self._model_repo_folder / self._model_repo_folder
/ self._default_models[backend_enum.value]["rec_keys_path"]["path"] / self._default_models[backend_enum.value]["rec_keys_path"]["path"]
) )
font_path = (
font_path
or artifacts_path
/ self._model_repo_folder
/ self._default_models[backend_enum.value]["font_path"]["path"]
)
for model_path in ( for model_path in (
rec_keys_path, rec_keys_path,
cls_model_path, cls_model_path,
rec_model_path, rec_model_path,
rec_keys_path, rec_keys_path,
font_path,
): ):
if model_path is None: if model_path is None:
continue continue