diff --git a/configs/rec/multi_language/generate_multi_language_configs.py b/configs/rec/multi_language/generate_multi_language_configs.py index d2302a41d14085395de0f82f4970bce7cdd7eb95..70b4aa74e60dbc20a50ab29754df867dee38aad9 100644 --- a/configs/rec/multi_language/generate_multi_language_configs.py +++ b/configs/rec/multi_language/generate_multi_language_configs.py @@ -28,15 +28,15 @@ support_list = { 'ug': 'uyghur', 'fa': 'persian', 'ur': 'urdu', - 'rs': 'serbian latin', + 'rs_latin': 'serbian latin', 'oc': 'occitan', - 'rsc': 'serbian cyrillic', + 'rs_cyrillic': 'serbian cyrillic', 'bg': 'bulgarian', 'uk': 'ukranian', 'be': 'belarusian', 'te': 'telugu', 'ka': 'kannada', - 'chinese_cht': 'chinese tradition', + 'ch_tra': 'chinese tradition', 'hi': 'hindi', 'mr': 'marathi', 'ne': 'nepali', diff --git a/doc/doc_ch/models_list.md b/doc/doc_ch/models_list.md index a17ee84e0ea110079dc6f497d07bd93055857a66..b421cbf40be67e968af6f4a6a0569e4f9595ceed 100755 --- a/doc/doc_ch/models_list.md +++ b/doc/doc_ch/models_list.md @@ -96,20 +96,20 @@ python3 generate_multi_language_configs.py -l it \ | ru_mobile_v2.0_rec |俄罗斯文识别|rec_ru_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ru_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ru_mobile_v2.0_rec_train.tar) | | ar_mobile_v2.0_rec |阿拉伯文识别|rec_ar_lite_train.yml|2.53M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ar_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ar_mobile_v2.0_rec_train.tar) | | hi_mobile_v2.0_rec |印地文识别|rec_hi_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/hi_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/hi_mobile_v2.0_rec_train.tar) | -| chinese_cht_mobile_v2.0_rec |中文繁体识别|rec_chinese_cht_lite_train.yml|5.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_train.tar) | +| ch_tramobile_v2.0_rec |中文繁体识别|rec_ch_tralite_train.yml|5.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ch_tramobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ch_tramobile_v2.0_rec_train.tar) | | ug_mobile_v2.0_rec |维吾尔文识别|rec_ug_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ug_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ug_mobile_v2.0_rec_train.tar) | | fa_mobile_v2.0_rec |波斯文识别|rec_fa_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/fa_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/fa_mobile_v2.0_rec_train.tar) | | ur_mobile_v2.0_rec |乌尔都文识别|rec_ur_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ur_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ur_mobile_v2.0_rec_train.tar) | -| rs_mobile_v2.0_rec |塞尔维亚文（latin）识别|rec_rs_lite_train.yml|2.53M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_mobile_v2.0_rec_train.tar) | +| rs_latin_mobile_v2.0_rec |塞尔维亚文（latin）识别|rec_rs_latin_lite_train.yml|2.53M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_latin_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_latin_mobile_v2.0_rec_train.tar) | | oc_mobile_v2.0_rec |欧西坦文识别|rec_oc_lite_train.yml|2.53M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/oc_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/oc_mobile_v2.0_rec_train.tar) | | mr_mobile_v2.0_rec |马拉地文识别|rec_mr_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/mr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/mr_mobile_v2.0_rec_train.tar) | | ne_mobile_v2.0_rec |尼泊尔文识别|rec_ne_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ne_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ne_mobile_v2.0_rec_train.tar) | -| rsc_mobile_v2.0_rec |塞尔维亚文（cyrillic）识别|rec_rsc_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rsc_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rsc_mobile_v2.0_rec_train.tar) | +| rs_cyrillic_mobile_v2.0_rec |塞尔维亚文（cyrillic）识别|rec_rs_cyrillic_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_cyrillic_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_cyrillic_mobile_v2.0_rec_train.tar) | | bg_mobile_v2.0_rec |保加利亚文识别|rec_bg_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/bg_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/bg_mobile_v2.0_rec_train.tar) | | uk_mobile_v2.0_rec |乌克兰文识别|rec_uk_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/uk_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/uk_mobile_v2.0_rec_train.tar) | | be_mobile_v2.0_rec |白俄罗斯文识别|rec_be_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/be_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/be_mobile_v2.0_rec_train.tar) | | te_mobile_v2.0_rec |泰卢固文识别|rec_te_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_train.tar) | -| ka_mobile_v2.0_rec |卡纳达文识别|rec_ka_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_train.tar) | +| kn_mobile_v2.0_rec |卡纳达文识别|rec_kn_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/kn_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/kn_mobile_v2.0_rec_train.tar) | | ta_mobile_v2.0_rec |泰米尔文识别|rec_ta_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_train.tar) | diff --git a/doc/doc_ch/recognition.md b/doc/doc_ch/recognition.md index 91d649078b3bccbf4e7a0858e90e422290e35cff..57bd6394220ac4ffec61e434f6fcb524f9ac92a9 100644 --- a/doc/doc_ch/recognition.md +++ b/doc/doc_ch/recognition.md @@ -351,7 +351,7 @@ PaddleOCR目前已支持26种（除中文外）语种识别，`configs/rec/multi | 配置文件 | 算法名称 | backbone | trans | seq | pred | language | character_type | | :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | :-----: | -| rec_chinese_cht_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 中文繁体 | chinese_cht| +| rec_ch_tra_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 中文繁体 | ch_tra| | rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 英语（区分大小写） | EN | | rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 法语 | french | | rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 德语 | german | @@ -366,16 +366,16 @@ PaddleOCR目前已支持26种（除中文外）语种识别，`configs/rec/multi | rec_ug_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 维吾尔语 | ug | | rec_fa_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 波斯语 | fa | | rec_ur_ite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 乌尔都语 | ur | -| rec_rs_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 塞尔维亚(latin)语 | rs | +| rec_rs_latin_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 塞尔维亚(latin)语 | rs_latin | | rec_oc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 欧西坦语 | oc | | rec_mr_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 马拉地语 | mr | | rec_ne_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 尼泊尔语 | ne | -| rec_rsc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 塞尔维亚(cyrillic)语 | rsc | +| rec_rs_cyrillic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 塞尔维亚(cyrillic)语 | rs_cyrillic | | rec_bg_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 保加利亚语 | bg | | rec_uk_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 乌克兰语 | uk | | rec_be_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 白俄罗斯语 | be | | rec_te_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 泰卢固语 | te | -| rec_ka_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 卡纳达语 | ka | +| rec_kn_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 卡纳达语 | kn | | rec_ta_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 泰米尔语 | ta | 多语言模型训练方式与中文模型一致，训练数据集均为100w的合成数据，少量的字体可以在 [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) 上下载，提取码：frgi。 diff --git a/doc/doc_en/models_list_en.md b/doc/doc_en/models_list_en.md index 1ef2835cd254e9d9b371a8d7fc54971e9e04f0be..25eb987e7d7c3a93589cf7be19b1d14064d52074 100755 --- a/doc/doc_en/models_list_en.md +++ b/doc/doc_en/models_list_en.md @@ -76,7 +76,7 @@ If you want to train your own model, you can prepare the training set file, veri cd {your/path/}PaddleOCR/configs/rec/multi_language/ # The -l or --language parameter is required # --train modify train_list path -# --val modify eval_list path +# --val modify eval_list path # --data_dir modify data dir # -o modify default parameters # --dict Change the dictionary path. The example uses the default dictionary path, so that this parameter can be empty. @@ -98,20 +98,20 @@ python3 generate_multi_language_configs.py -l it \ | ru_mobile_v2.0_rec |Lightweight model for Russia recognition|rec_ru_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ru_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ru_mobile_v2.0_rec_train.tar) | | ar_mobile_v2.0_rec |Lightweight model for Arabic recognition|rec_ar_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ar_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ar_mobile_v2.0_rec_train.tar) | | hi_mobile_v2.0_rec |Lightweight model for Hindi recognition|rec_hi_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/hi_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/hi_mobile_v2.0_rec_train.tar) | -| chinese_cht_mobile_v2.0_rec |Lightweight model for chinese traditional recognition|rec_chinese_cht_lite_train.yml|5.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_train.tar) | +| ch_tra_mobile_v2.0_rec |Lightweight model for chinese traditional recognition|rec_ch_tra_lite_train.yml|5.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ch_tra_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ch_tra_mobile_v2.0_rec_train.tar) | | ug_mobile_v2.0_rec |Lightweight model for Uyghur recognition|rec_ug_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ug_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ug_mobile_v2.0_rec_train.tar) | | fa_mobile_v2.0_rec |Lightweight model for Persian recognition|rec_fa_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/fa_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/fa_mobile_v2.0_rec_train.tar) | | ur_mobile_v2.0_rec |Lightweight model for Urdu recognition|rec_ur_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ur_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ur_mobile_v2.0_rec_train.tar) | -| rs_mobile_v2.0_rec |Lightweight model for Serbian(latin) recognition|rec_rs_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_mobile_v2.0_rec_train.tar) | +| rs_latin_mobile_v2.0_rec |Lightweight model for Serbian(latin) recognition|rec_rs_latin_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_latin_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_latin_mobile_v2.0_rec_train.tar) | | oc_mobile_v2.0_rec |Lightweight model for Occitan recognition|rec_oc_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/oc_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/oc_mobile_v2.0_rec_train.tar) | | mr_mobile_v2.0_rec |Lightweight model for Marathi recognition|rec_mr_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/mr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/mr_mobile_v2.0_rec_train.tar) | | ne_mobile_v2.0_rec |Lightweight model for Nepali recognition|rec_ne_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ne_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ne_mobile_v2.0_rec_train.tar) | -| rsc_mobile_v2.0_rec |Lightweight model for Serbian(cyrillic) recognition|rec_rsc_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rsc_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rsc_mobile_v2.0_rec_train.tar) | +| rs_cyrillic_mobile_v2.0_rec |Lightweight model for Serbian(cyrillic) recognition|rec_rs_cyrillic_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_cyrillic_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_cyrillic_mobile_v2.0_rec_train.tar) | | bg_mobile_v2.0_rec |Lightweight model for Bulgarian recognition|rec_bg_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/bg_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/bg_mobile_v2.0_rec_train.tar) | | uk_mobile_v2.0_rec |Lightweight model for Ukranian recognition|rec_uk_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/uk_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/uk_mobile_v2.0_rec_train.tar) | | be_mobile_v2.0_rec |Lightweight model for Belarusian recognition|rec_be_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/be_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/be_mobile_v2.0_rec_train.tar) | | te_mobile_v2.0_rec |Lightweight model for Telugu recognition|rec_te_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_train.tar) | -| ka_mobile_v2.0_rec |Lightweight model for Kannada recognition|rec_ka_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_train.tar) | +| kn_mobile_v2.0_rec |Lightweight model for Kannada recognition|rec_kn_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/kn_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/kn_mobile_v2.0_rec_train.tar) | | ta_mobile_v2.0_rec |Lightweight model for Tamil recognition|rec_ta_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_train.tar) | diff --git a/doc/doc_en/recognition_en.md b/doc/doc_en/recognition_en.md index 14ddcc755071924a91b9bf654fb2f0b314e00790..f21da7aad8e0a04e900d6c35706575772cbe39f8 100644 --- a/doc/doc_en/recognition_en.md +++ b/doc/doc_en/recognition_en.md @@ -353,31 +353,31 @@ Currently, the multi-language algorithms supported by PaddleOCR are: | Configuration file | Algorithm name | backbone | trans | seq | pred | language | character_type | | :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | :-----: | -| rec_chinese_cht_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | chinese traditional | chinese_cht| +| rec_ch_tra_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | chinese traditional | ch_tra| | rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | English(Case sensitive) | EN | | rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | French | french | | rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | German | german | | rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Japanese | japan | | rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Korean | korean | | rec_it_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Italian | it | -| rec_xi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Spanish | xi | -| rec_pu_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Portuguese | pu | +| rec_xi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Spanish | es | +| rec_pu_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Portuguese | pt | | rec_ru_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Russia | ru | | rec_ar_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Arabic | ar | | rec_hi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Hindi | hi | | rec_ug_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Uyghur | ug | | rec_fa_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Persian(Farsi) | fa | | rec_ur_ite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Urdu | ur | -| rec_rs_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Serbian(latin) | rs | +| rec_rs_latin_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Serbian(latin) | rs_latin | | rec_oc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Occitan | oc | | rec_mr_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Marathi | mr | | rec_ne_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Nepali | ne | -| rec_rsc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Serbian(cyrillic) | rsc | +| rec_rs_cyrillic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Serbian(cyrillic) | rs_cyrillic | | rec_bg_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Bulgarian | bg | | rec_uk_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Ukranian | uk | | rec_be_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Belarusian | be | | rec_te_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Telugu | te | -| rec_ka_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Kannada | ka | +| rec_kn_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | kannada | kn | | rec_ta_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Tamil | ta | diff --git a/doc/imgs_words/kannada/ka_1.jpg b/doc/imgs_words/kannada/kn_1.jpg similarity index 100% rename from doc/imgs_words/kannada/ka_1.jpg rename to doc/imgs_words/kannada/kn_1.jpg diff --git a/doc/imgs_words/kannada/ka_2.jpg b/doc/imgs_words/kannada/kn_2.jpg similarity index 100% rename from doc/imgs_words/kannada/ka_2.jpg rename to doc/imgs_words/kannada/kn_2.jpg diff --git a/doc/imgs_words/portuguese/pu_1.jpg b/doc/imgs_words/portuguese/pt_1.jpg similarity index 100% rename from doc/imgs_words/portuguese/pu_1.jpg rename to doc/imgs_words/portuguese/pt_1.jpg diff --git a/doc/imgs_words/portuguese/pu_2.jpg b/doc/imgs_words/portuguese/pt_2.jpg similarity index 100% rename from doc/imgs_words/portuguese/pu_2.jpg rename to doc/imgs_words/portuguese/pt_2.jpg diff --git a/doc/imgs_words/spanish/xi_1.jpg b/doc/imgs_words/spanish/es_1.jpg similarity index 100% rename from doc/imgs_words/spanish/xi_1.jpg rename to doc/imgs_words/spanish/es_1.jpg diff --git a/doc/imgs_words/spanish/xi_2.jpg b/doc/imgs_words/spanish/es_2.jpg similarity index 100% rename from doc/imgs_words/spanish/xi_2.jpg rename to doc/imgs_words/spanish/es_2.jpg diff --git a/ppocr/data/imaug/label_ops.py b/ppocr/data/imaug/label_ops.py index 75c6530d22c5b0d5ad9c0c4414132ec5fa4e3dd1..16659773ee27c9bb396fd684ce6bab5c8ef95083 100644 --- a/ppocr/data/imaug/label_ops.py +++ b/ppocr/data/imaug/label_ops.py @@ -94,9 +94,9 @@ class BaseRecLabelEncode(object): use_space_char=False): support_character_type = [ 'ch', 'en', 'EN_symbol', 'french', 'german', 'japan', 'korean', - 'EN', 'it', 'es', 'pt', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs', - 'oc', 'rsc', 'bg', 'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi', - 'mr', 'ne' + 'EN', 'it', 'es', 'pt', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', + 'rs_latin', 'oc', 'rs_cyrillic', 'bg', 'uk', 'be', 'te', 'ka', + 'ch_tra', 'hi', 'mr', 'ne' ] assert character_type in support_character_type, "Only {} are supported now but get {}".format( support_character_type, character_type) diff --git a/ppocr/postprocess/rec_postprocess.py b/ppocr/postprocess/rec_postprocess.py index af243caa44e8390657b7a95e971aede0c0f90edd..2988e1231b58ec0bcc8741042626ee4d3b8fe03d 100644 --- a/ppocr/postprocess/rec_postprocess.py +++ b/ppocr/postprocess/rec_postprocess.py @@ -26,9 +26,9 @@ class BaseRecLabelDecode(object): use_space_char=False): support_character_type = [ 'ch', 'en', 'EN_symbol', 'french', 'german', 'japan', 'korean', - 'it', 'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs', 'oc', - 'rsc', 'bg', 'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi', 'mr', - 'ne', 'EN' + 'it', 'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs_latin', + 'oc', 'rs_cyrillic', 'bg', 'uk', 'be', 'te', 'ka', 'ch_tra', 'hi', + 'mr', 'ne', 'EN' ] assert character_type in support_character_type, "Only {} are supported now but get {}".format( support_character_type, character_type) diff --git a/ppocr/utils/dict/chinese_cht_dict.txt b/ppocr/utils/dict/ch_tra_dict.txt similarity index 100% rename from ppocr/utils/dict/chinese_cht_dict.txt rename to ppocr/utils/dict/ch_tra_dict.txt diff --git a/ppocr/utils/dict/ic15_dict.txt b/ppocr/utils/dict/ic15_dict.txt new file mode 100644 index 0000000000000000000000000000000000000000..01f4c698071f43f25e90f4a2580b940773ea2b80 --- /dev/null +++ b/ppocr/utils/dict/ic15_dict.txt @@ -0,0 +1,37 @@ +0 +1 +2 +3 +4 +5 +6 +7 +8 +9 +A +B +C +D +E +F +G +H +I +J +K +L +M +N +O +P +Q +R +S +T +U +V +W +X +Y +Z +: \ No newline at end of file diff --git a/ppocr/utils/dict/ka_dict.txt b/ppocr/utils/dict/kn_dict.txt similarity index 100% rename from ppocr/utils/dict/ka_dict.txt rename to ppocr/utils/dict/kn_dict.txt diff --git a/ppocr/utils/dict/rsc_dict.txt b/ppocr/utils/dict/rs_cyrillic_dict.txt similarity index 100% rename from ppocr/utils/dict/rsc_dict.txt rename to ppocr/utils/dict/rs_cyrillic_dict.txt diff --git a/ppocr/utils/dict/rs_dict.txt b/ppocr/utils/dict/rs_latin_dict.txt similarity index 100% rename from ppocr/utils/dict/rs_dict.txt rename to ppocr/utils/dict/rs_latin_dict.txt