yujunjun/PaddleOCR
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2025-06-26 21:24:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Enhance OCR model selection logic (#15643)

Browse Source 
If there is no model specified select the best available model
for the specified language

Fix #15642
This commit is contained in:
timminator 2025-06-09 05:21:39 +02:00 committed by GitHub
parent b0e622937a
commit ae21c3d3a9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 105 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

194
paddleocr/_pipelines/ocr.py
View File

@ -295,10 +295,112 @@ class PaddleOCR(PaddleXPipelineWrapper):
return create_config_from_structure(STRUCTURE)
def _get_ocr_model_names(self, lang, ppocr_version):
LATIN_LANGS = [
"af",
"az",
"bs",
"cs",
"cy",
"da",
"de",
"es",
"et",
"fr",
"ga",
"hr",
"hu",
"id",
"is",
"it",
"ku",
"la",
"lt",
"lv",
"mi",
"ms",
"mt",
"nl",
"no",
"oc",
"pi",
"pl",
"pt",
"ro",
"rs_latin",
"sk",
"sl",
"sq",
"sv",
"sw",
"tl",
"tr",
"uz",
"vi",
"french",
"german",
]
ARABIC_LANGS = ["ar", "fa", "ug", "ur"]
CYRILLIC_LANGS = [
"ru",
"rs_cyrillic",
"be",
"bg",
"uk",
"mn",
"abq",
"ady",
"kbd",
"ava",
"dar",
"inh",
"che",
"lbe",
"lez",
"tab",
]
DEVANAGARI_LANGS = [
"hi",
"mr",
"ne",
"bh",
"mai",
"ang",
"bho",
"mah",
"sck",
"new",
"gom",
"sa",
"bgc",
]
SPECIFIC_LANGS = [
"ch",
"en",
"korean",
"japan",
"chinese_cht",
"te",
"ka",
"ta",
]
if lang is None:
lang = "ch"
if ppocr_version is None:
ppocr_version = "PP-OCRv5"
if lang in ("ch", "chinese_cht", "en", "japan"):
ppocr_version = "PP-OCRv5"
elif lang in (
LATIN_LANGS
+ ARABIC_LANGS
+ CYRILLIC_LANGS
+ DEVANAGARI_LANGS
+ SPECIFIC_LANGS
):
ppocr_version = "PP-OCRv3"
else:
# Unknown language specified
return None, None
if ppocr_version == "PP-OCRv5":
if lang in ("ch", "chinese_cht", "en", "japan"):
@ -314,84 +416,6 @@ class PaddleOCR(PaddleXPipelineWrapper):
return None, None
else:
# PP-OCRv3
LATIN_LANGS = [
"af",
"az",
"bs",
"cs",
"cy",
"da",
"de",
"es",
"et",
"fr",
"ga",
"hr",
"hu",
"id",
"is",
"it",
"ku",
"la",
"lt",
"lv",
"mi",
"ms",
"mt",
"nl",
"no",
"oc",
"pi",
"pl",
"pt",
"ro",
"rs_latin",
"sk",
"sl",
"sq",
"sv",
"sw",
"tl",
"tr",
"uz",
"vi",
"french",
"german",
]
ARABIC_LANGS = ["ar", "fa", "ug", "ur"]
CYRILLIC_LANGS = [
"ru",
"rs_cyrillic",
"be",
"bg",
"uk",
"mn",
"abq",
"ady",
"kbd",
"ava",
"dar",
"inh",
"che",
"lbe",
"lez",
"tab",
]
DEVANAGARI_LANGS = [
"hi",
"mr",
"ne",
"bh",
"mai",
"ang",
"bho",
"mah",
"sck",
"new",
"gom",
"sa",
"bgc",
]
rec_lang = None
if lang in LATIN_LANGS:
rec_lang = "latin"
@ -402,17 +426,9 @@ class PaddleOCR(PaddleXPipelineWrapper):
elif lang in DEVANAGARI_LANGS:
rec_lang = "devanagari"
else:
if lang in [
"ch",
"en",
"korean",
"japan",
"chinese_cht",
"te",
"ka",
"ta",
]:
if lang in SPECIFIC_LANGS:
rec_lang = lang
rec_model_name = None
if rec_lang == "ch":
rec_model_name = "PP-OCRv3_mobile_rec"