Note : Compared with models 1.1, which are trained with static graph programming paradigm, models 2.0 are the dynamic graph trained version and achieve close performance.
The downloadable models provided by PaddleOCR include inference model, trained model, pre-trained model and slim model. The differences between the models are as follows:
| model type | model format | description |
|---|---|---|
| inference model | inference.pdmodel、inference.pdiparams | Used for reasoning based on Python prediction engine，detail |
| trained model, pre-trained model | *.pdparams、*.pdopt、*.states | The checkpoints model saved in the training process, which stores the parameters of the model, mostly used for model evaluation and continuous training. |
| slim model | *.nb | Generally used for Lite deployment |
| model name | description | config | model size | download |
|---|---|---|---|---|
| ch_ppocr_mobile_slim_v2.0_det | Slim pruned lightweight model, supporting Chinese, English, multilingual text detection | ch_det_mv3_db_v2.0.yml | inference model (coming soon) / slim model (coming soon) | |
| ch_ppocr_mobile_v2.0_det | Original lightweight model, supporting Chinese, English, multilingual text detection | ch_det_mv3_db_v2.0.yml | 3M | inference model / trained model |
| ch_ppocr_server_v2.0_det | General model, which is larger than the lightweight model, but achieved better performance | ch_det_res18_db_v2.0.yml | 47M | inference model / trained model |
| model name | description | config | model size | download |
|---|---|---|---|---|
| ch_ppocr_mobile_slim_v2.0_rec | Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition | rec_chinese_lite_train_v2.0.yml | inference model (coming soon) / slim model (coming soon) | |
| ch_ppocr_mobile_v2.0_rec | Original lightweight model, supporting Chinese, English and number recognition | rec_chinese_lite_train_v2.0.yml | 3.71M | inference model / trained model / pre-trained model |
| ch_ppocr_server_v2.0_rec | General model, supporting Chinese, English and number recognition | rec_chinese_common_train_v2.0.yml | 94.8M | inference model / trained model / pre-trained model |
Note: The trained model is finetuned on the pre-trained model with real data and synthsized vertical text data, which achieved better performance in real scene. The pre-trained model is directly trained on the full amount of real data and synthsized data, which is more suitable for finetune on your own dataset.
| model name | description | config | model size | download |
|---|---|---|---|---|
| en_number_mobile_slim_v2.0_rec | Slim pruned and quantized lightweight model, supporting English and number recognition | rec_en_number_lite_train.yml | inference model (coming soon ) / slim model (coming soon) | |
| en_number_mobile_v2.0_rec | Original lightweight model, supporting English and number recognition | rec_en_number_lite_train.yml | 2.56M | inference model / trained model |
Note： The configuration file of the new multi language model is generated by code. Take the Italian configuration file as an example：
# The code needs to run in the specified directory
cd PaddleOCR/configs/rec/multi_language/
# Set the required language configuration file through -l or --language parameter
# This command will write the default parameter to the configuration file.
python3 generate_multi_language_configs.py -l itYou can use the --help parameter to check which multi language are supported by current PaddleOCR.
python3 generate_multi_language_configs.py --helpIf you don't want to use the default path or default parameters, you can modify them according to the following command：
# The -l or --language parameter is required
# --train modify train_list path
# --val modify eval_list path
# --data_dir modify data dir
# -o modify default parameters
python3 generate_multi_language_configs.py -l it \
--train {path/to/train_list} \
--val {path/to/val_list} \
--data_dir {path/to/data_dir} \
-o Global.use_gpu=False| model name | description | config | model size | download |
|---|---|---|---|---|
| french_mobile_v2.0_rec | Lightweight model for French recognition | rec_french_lite_train.yml | 2.65M | inference model / trained model |
| german_mobile_v2.0_rec | Lightweight model for French recognition | rec_german_lite_train.yml | 2.65M | inference model / trained model |
| korean_mobile_v2.0_rec | Lightweight model for Korean recognition | rec_korean_lite_train.yml | 3.9M | inference model / trained model |
| japan_mobile_v2.0_rec | Lightweight model for Japanese recognition | rec_japan_lite_train.yml | 4.23M | inference model / trained model |
| it_mobile_v2.0_rec | Lightweight model for Italian recognition | rec_it_lite_train.yml | 2.53M | inference mode / trained mode |
| xi_mobile_v2.0_rec | Lightweight model for Spanish recognition | rec_xi_lite_train.yml | 2.53M | inference mode / trained mode |
| pu_mobile_v2.0_rec | Lightweight model for Portuguese recognition | rec_pu_lite_train.yml | 2.63M | inference mode / trained mode |
| ru_mobile_v2.0_rec | Lightweight model for Russia recognition | rec_ru_lite_train.yml | 2.63M | inference mode / trained mode |
| ar_mobile_v2.0_rec | Lightweight model for Arabic recognition | rec_ar_lite_train.yml | 2.53M | inference mode / trained mode |
| hi_mobile_v2.0_rec | Lightweight model for Hindi recognition | rec_hi_lite_train.yml | 2.63M | inference mode / trained mode |
| chinese_cht_mobile_v2.0_rec | Lightweight model for chinese traditional recognition | rec_chinese_cht_lite_train.yml | 5.63M | inference mode / trained mode |
| ug_mobile_v2.0_rec | Lightweight model for Uyghur recognition | rec_ug_lite_train.yml | 2.63M | inference mode / trained mode |
| fa_mobile_v2.0_rec | Lightweight model for Persian recognition | rec_fa_lite_train.yml | 2.63M | inference mode / trained mode |
| ur_mobile_v2.0_rec | Lightweight model for Urdu recognition | rec_ur_lite_train.yml | 2.63M | inference mode / trained mode |
| rs_mobile_v2.0_rec | Lightweight model for Serbian(latin) recognition | rec_rs_lite_train.yml | 2.53M | inference mode / trained mode |
| oc_mobile_v2.0_rec | Lightweight model for Occitan recognition | rec_oc_lite_train.yml | 2.53M | inference mode / trained mode |
| mr_mobile_v2.0_rec | Lightweight model for Marathi recognition | rec_mr_lite_train.yml | 2.63M | inference mode / trained mode |
| ne_mobile_v2.0_rec | Lightweight model for Nepali recognition | rec_ne_lite_train.yml | 2.63M | inference mode / trained mode |
| rsc_mobile_v2.0_rec | Lightweight model for Serbian(cyrillic) recognition | rec_rsc_lite_train.yml | 2.63M | inference mode / trained mode |
| bg_mobile_v2.0_rec | Lightweight model for Bulgarian recognition | rec_bg_lite_train.yml | 2.63M | inference mode / trained mode |
| uk_mobile_v2.0_rec | Lightweight model for Ukranian recognition | rec_uk_lite_train.yml | 2.63M | inference mode / trained mode |
| be_mobile_v2.0_rec | Lightweight model for Belarusian recognition | rec_be_lite_train.yml | 2.63M | inference mode / trained mode |
| te_mobile_v2.0_rec | Lightweight model for Telugu recognition | rec_te_lite_train.yml | 2.63M | inference mode / trained mode |
| ka_mobile_v2.0_rec | Lightweight model for Kannada recognition | [rec_ka_lite_train.yml | 2.63M | inference mode / trained mode |
| ta_mobile_v2.0_rec | Lightweight model for Tamil recognition | rec_ta_lite_train.yml | 2.63M | inference mode / trained mode |
| model name | description | config | model size | download |
|---|---|---|---|---|
| ch_ppocr_mobile_slim_v2.0_cls | Slim quantized model | cls_mv3.yml | inference model (coming soon) / trained model / slim model | |
| ch_ppocr_mobile_v2.0_cls | Original model | cls_mv3.yml | 1.38M | inference model / trained model |