Skip to content

Commit bd147c6

Browse files
committed
update whl for multi lang rec
1 parent 1795bb1 commit bd147c6

File tree

3 files changed

+69
-3
lines changed

3 files changed

+69
-3
lines changed

doc/doc_ch/whl.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -416,4 +416,4 @@ im_show.save('result.jpg')
416416
| cls | 前向时是否启动分类 (命令行模式下使用use_angle_cls控制前向是否启动分类) | FALSE |
417417
| show_log | 是否打印logger信息 | FALSE |
418418
| type | 执行ocr或者表格结构化, 值可选['ocr','structure'] | ocr |
419-
| ocr_version | OCR模型版本,可选PP-OCRv3, PP-OCRv2, PP-OCR。PP-OCRv3 目前仅支持中、英文的检测和识别模型,方向分类器模型;PP-OCRv2 目前仅支持中文的检测和识别模型;PP-OCR支持中文的检测,识别,多语种识别,方向分类器等模型 | PP-OCRv3 |
419+
| ocr_version | OCR模型版本,可选PP-OCRv3, PP-OCRv2, PP-OCR。PP-OCRv3 支持中、英文的检测、识别、多语种识别,方向分类器等模型;PP-OCRv2 目前仅支持中文的检测和识别模型;PP-OCR支持中文的检测,识别,多语种识别,方向分类器等模型 | PP-OCRv3 |

doc/doc_en/whl_en.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -368,4 +368,4 @@ im_show.save('result.jpg')
368368
| cls | Enable classification when `ppocr.ocr` func exec((Use use_angle_cls in command line mode to control whether to start classification in the forward direction) | FALSE |
369369
| show_log | Whether to print log| FALSE |
370370
| type | Perform ocr or table structuring, the value is selected in ['ocr','structure'] | ocr |
371-
| ocr_version | OCR Model version number, the current model support list is as follows: PP-OCRv3 support Chinese and English detection and recognition model and direction classifier model, PP-OCRv2 support Chinese detection and recognition model, PP-OCR support Chinese detection, recognition and direction classifier, multilingual recognition model | PP-OCRv3 |
371+
| ocr_version | OCR Model version number, the current model support list is as follows: PP-OCRv3 supports Chinese and English detection, recognition, multilingual recognition, direction classifier models, PP-OCRv2 support Chinese detection and recognition model, PP-OCR support Chinese detection, recognition and direction classifier, multilingual recognition model | PP-OCRv3 |

paddleocr.py

Lines changed: 67 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -67,6 +67,10 @@
6767
'url':
6868
'https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar',
6969
},
70+
'ml': {
71+
'url':
72+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_infer.tar'
73+
}
7074
},
7175
'rec': {
7276
'ch': {
@@ -79,6 +83,66 @@
7983
'https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar',
8084
'dict_path': './ppocr/utils/en_dict.txt'
8185
},
86+
'french': {
87+
'url':
88+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_ppocr_PP-OCRv3_rec_infer.tar',
89+
'dict_path': './ppocr/utils/dict/latin_dict.txt'
90+
},
91+
'german': {
92+
'url':
93+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_ppocr_PP-OCRv3_rec_infer.tar',
94+
'dict_path': './ppocr/utils/dict/latin_dict.txt'
95+
},
96+
'korean': {
97+
'url':
98+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/korean_PP-OCRv3_rec_infer.tar',
99+
'dict_path': './ppocr/utils/dict/korean_dict.txt'
100+
},
101+
'japan': {
102+
'url':
103+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/japan_PP-OCRv3_rec_infer.tar',
104+
'dict_path': './ppocr/utils/dict/japan_dict.txt'
105+
},
106+
'chinese_cht': {
107+
'url':
108+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/chinese_cht_PP-OCRv3_rec_infer.tar',
109+
'dict_path': './ppocr/utils/dict/chinese_cht_dict.txt'
110+
},
111+
'ta': {
112+
'url':
113+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ta_PP-OCRv3_rec_infer.tar',
114+
'dict_path': './ppocr/utils/dict/ta_dict.txt'
115+
},
116+
'te': {
117+
'url':
118+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/te_PP-OCRv3_rec_infer.tar',
119+
'dict_path': './ppocr/utils/dict/te_dict.txt'
120+
},
121+
'ka': {
122+
'url':
123+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ka_PP-OCRv3_rec_infer.tar',
124+
'dict_path': './ppocr/utils/dict/ka_dict.txt'
125+
},
126+
'latin': {
127+
'url':
128+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_ppocr_PP-OCRv3_rec_infer.tar',
129+
'dict_path': './ppocr/utils/dict/latin_dict.txt'
130+
},
131+
'arabic': {
132+
'url':
133+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/arabic_ppocr_PP-OCRv3_rec_infer.tar',
134+
'dict_path': './ppocr/utils/dict/arabic_dict.txt'
135+
},
136+
'cyrillic': {
137+
'url':
138+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/cyrillic_ppocr_PP-OCRv3_rec_infer.tar',
139+
'dict_path': './ppocr/utils/dict/cyrillic_dict.txt'
140+
},
141+
'devanagari': {
142+
'url':
143+
'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/devanagari_ppocr_PP-OCRv3_rec_infer.tar',
144+
'dict_path': './ppocr/utils/dict/devanagari_dict.txt'
145+
},
82146
},
83147
'cls': {
84148
'ch': {
@@ -259,7 +323,7 @@ def parse_lang(lang):
259323
'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga', 'hr',
260324
'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms', 'mt', 'nl',
261325
'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin', 'sk', 'sl', 'sq', 'sv',
262-
'sw', 'tl', 'tr', 'uz', 'vi'
326+
'sw', 'tl', 'tr', 'uz', 'vi', 'french', 'german'
263327
]
264328
arabic_lang = ['ar', 'fa', 'ug', 'ur']
265329
cyrillic_lang = [
@@ -285,6 +349,8 @@ def parse_lang(lang):
285349
det_lang = "ch"
286350
elif lang == 'structure':
287351
det_lang = 'structure'
352+
elif lang == "ml":
353+
det_lang = "ml"
288354
else:
289355
det_lang = "en"
290356
return lang, det_lang

0 commit comments

Comments
 (0)