diff --git a/configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..0ad1ab0adc189102ff07094fcda92d4f9ea9c662 --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_arabic_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/arabic_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_arabic.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/configs/rec/PP-OCRv3/multi_language/chinese_cht_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/chinese_cht_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..28e0c10aa0f83fdf8e621aae04bf2b7374255adc --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/chinese_cht_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_chinese_cht_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/chinese_cht_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_chinese_cht.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/configs/rec/PP-OCRv3/multi_language/cyrillic_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/cyrillic_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..fbdbe6c44c689ea267c9995f832305d800046edb --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/cyrillic_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_cyrillic_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/cyrillic_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_cyrillic.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/configs/rec/PP-OCRv3/multi_language/devanagari_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/devanagari_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..48eb38df36f931b76b8e9fb8369daf06ad037d25 --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/devanagari_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_devanagari_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/devanagari_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_devanagari.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/configs/rec/PP-OCRv3/multi_language/japan_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/japan_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..6cab0d447247e28bb58b30384d4f9d032d6ce9d0 --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/japan_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_japan_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/japan_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_japan.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/configs/rec/PP-OCRv3/multi_language/ka_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/ka_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..7a9c8241d1564e5f1295655ba64694a117064bd8 --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/ka_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_ka_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/ka_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_ka.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/configs/rec/PP-OCRv3/multi_language/korean_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/korean_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..29ff570772a621ba747e0388bcc0c042db0dba43 --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/korean_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_korean_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/korean_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_korean.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/configs/rec/PP-OCRv3/multi_language/latin_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/latin_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..1784bfe611366c45230fd2abf69ab16e3a1c3ae9 --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/latin_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_latin_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/latin_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_latin.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/configs/rec/PP-OCRv3/multi_language/ta_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/ta_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..70b26aa84a2178111edab9f094c369c5d22e31a9 --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/ta_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_ta_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/ta_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_ta.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/configs/rec/PP-OCRv3/multi_language/te_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/te_PP-OCRv3_rec.yml new file mode 100644 index 0000000000000000000000000000000000000000..3617af79e3b9c5a55ef22d549465ba2109618e32 --- /dev/null +++ b/configs/rec/PP-OCRv3/multi_language/te_PP-OCRv3_rec.yml @@ -0,0 +1,131 @@ +Global: + debug: false + use_gpu: true + epoch_num: 500 + log_smooth_window: 20 + print_batch_step: 10 + save_model_dir: ./output/v3_te_mobile + save_epoch_step: 3 + eval_batch_step: [0, 2000] + cal_metric_during_train: true + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: false + infer_img: doc/imgs_words/ch/word_1.jpg + character_dict_path: ppocr/utils/dict/te_dict.txt + max_text_length: &max_text_length 25 + infer_mode: false + use_space_char: true + distributed: true + save_res_path: ./output/rec/predicts_ppocrv3_te.txt + + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + name: Cosine + learning_rate: 0.001 + warmup_epoch: 5 + regularizer: + name: L2 + factor: 3.0e-05 + + +Architecture: + model_type: rec + algorithm: SVTR + Transform: + Backbone: + name: MobileNetV1Enhance + scale: 0.5 + last_conv_stride: [1, 2] + last_pool_type: avg + Head: + name: MultiHead + head_list: + - CTCHead: + Neck: + name: svtr + dims: 64 + depth: 2 + hidden_dims: 120 + use_guide: True + Head: + fc_decay: 0.00001 + - SARHead: + enc_dim: 512 + max_text_length: *max_text_length + +Loss: + name: MultiLoss + loss_config_list: + - CTCLoss: + - SARLoss: + +PostProcess: + name: CTCLabelDecode + +Metric: + name: RecMetric + main_indicator: acc + ignore_space: False + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/ + ext_op_transform_idx: 1 + label_file_list: + - ./train_data/train_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - RecConAug: + prob: 0.5 + ext_data_num: 2 + image_shape: [48, 320, 3] + - RecAug: + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: true + batch_size_per_card: 128 + drop_last: true + num_workers: 4 +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data + label_file_list: + - ./train_data/val_list.txt + transforms: + - DecodeImage: + img_mode: BGR + channel_first: false + - MultiLabelEncode: + - RecResizeImg: + image_shape: [3, 48, 320] + - KeepKeys: + keep_keys: + - image + - label_ctc + - label_sar + - length + - valid_ratio + loader: + shuffle: false + drop_last: false + batch_size_per_card: 128 + num_workers: 4 diff --git a/deploy/pdserving/config.yml b/deploy/pdserving/config.yml index 6e30a626d0cdb0b4e5fe6feb737ea46c2bc59f90..19cd9325ee8b241fd591678b9ba6452de9bec025 100644 --- a/deploy/pdserving/config.yml +++ b/deploy/pdserving/config.yml @@ -37,7 +37,7 @@ op: model_config: ./ppocr_det_v3_serving #Fetch结果列表,以client_config中fetch_var的alias_name为准 - fetch_list: ["save_infer_model/scale_0.tmp_1"] + fetch_list: ["sigmoid_0.tmp_0"] #计算硬件ID,当devices为""或不写时为CPU预测;当devices为"0", "0,1,2"时为GPU预测,表示使用的GPU卡 devices: "0" diff --git a/deploy/pdserving/web_service.py b/deploy/pdserving/web_service.py index 07fd6102beaef4001f87574a2f0631e2b1012613..98e2dfba2f5abd3fc36bf3743b23f7eb7be3b9c4 100644 --- a/deploy/pdserving/web_service.py +++ b/deploy/pdserving/web_service.py @@ -56,7 +56,7 @@ class DetOp(Op): return {"x": det_img[np.newaxis, :].copy()}, False, None, "" def postprocess(self, input_dicts, fetch_dict, data_id, log_id): - det_out = fetch_dict["save_infer_model/scale_0.tmp_1"] + det_out = fetch_dict["sigmoid_0.tmp_0"] ratio_list = [ float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w ] diff --git a/deploy/pdserving/web_service_det.py b/deploy/pdserving/web_service_det.py index 0ca8dbc41bbdde4caf76bcfddabe4b9c2e94cb4b..7584608a9fed4bea93caa5c814c0450566696d56 100644 --- a/deploy/pdserving/web_service_det.py +++ b/deploy/pdserving/web_service_det.py @@ -55,7 +55,7 @@ class DetOp(Op): return {"x": det_img[np.newaxis, :].copy()}, False, None, "" def postprocess(self, input_dicts, fetch_dict, data_id, log_id): - det_out = fetch_dict["save_infer_model/scale_0.tmp_1"] + det_out = fetch_dict["sigmoid_0.tmp_0"] ratio_list = [ float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w ] diff --git a/doc/doc_ch/models_list.md b/doc/doc_ch/models_list.md index e0356e89e7c1c9998c953f104891a2f4b577e2de..a8d99b51f17fa0912de77418e24d08ab10774c2c 100644 --- a/doc/doc_ch/models_list.md +++ b/doc/doc_ch/models_list.md @@ -81,7 +81,7 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 |模型名称|模型简介|配置文件|推理模型大小|下载地址| | --- | --- | --- | --- | --- | -|ch_PP-OCRv3_rec_slim |【最新】slim量化版超轻量模型,支持中英文、数字识别|[ch_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml)| 4.9M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/ch/ch_PP-OCRv3_rec_slim_train.tar) / [slim模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.nb) | +|ch_PP-OCRv3_rec_slim |【最新】slim量化版超轻量模型,支持中英文、数字识别|[ch_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml)| 4.9M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_train.tar) / [slim模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.nb) | |ch_PP-OCRv3_rec|【最新】原始超轻量模型,支持中英文、数字识别|[ch_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml)| 12.4M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) | |ch_PP-OCRv2_rec_slim| slim量化版超轻量模型,支持中英文、数字识别|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)| 9M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_train.tar) | |ch_PP-OCRv2_rec| 原始超轻量模型,支持中英文、数字识别|[ch_PP-OCRv2_rec_distillation.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml)|8.5M|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) | @@ -96,7 +96,7 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 |模型名称|模型简介|配置文件|推理模型大小|下载地址| | --- | --- | --- | --- | --- | -|en_PP-OCRv3_rec_slim |【最新】slim量化版超轻量模型,支持英文、数字识别 | [en_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml)| - |[推理模型(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.tar) / [训练模型(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_train.tar) / [slim模型(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.nb) | +|en_PP-OCRv3_rec_slim |【最新】slim量化版超轻量模型,支持英文、数字识别 | [en_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml)| - |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_train.tar) / [slim模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.nb) | |ch_PP-OCRv3_rec |【最新】原始超轻量模型,支持英文、数字识别|[en_PP-OCRv3_rec.yml](../../configs/rec/en_PP-OCRv3/en_PP-OCRv3_rec.yml)| 9.6M | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) | |en_number_mobile_slim_v2.0_rec|slim裁剪量化版超轻量模型,支持英文、数字识别|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)| 2.7M | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/en_number_mobile_v2.0_rec_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/en_number_mobile_v2.0_rec_slim_train.tar) | |en_number_mobile_v2.0_rec|原始超轻量模型,支持英文、数字识别|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)|2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_train.tar) | @@ -107,18 +107,17 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 |模型名称|字典文件|模型简介|配置文件|推理模型大小|下载地址| | --- | --- | --- | --- |--- | --- | -| french_mobile_v2.0_rec | ppocr/utils/dict/french_dict.txt |法文识别|[rec_french_lite_train.yml](../../configs/rec/multi_language/rec_french_lite_train.yml)|2.65M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_train.tar) | -| german_mobile_v2.0_rec | ppocr/utils/dict/german_dict.txt |德文识别|[rec_german_lite_train.yml](../../configs/rec/multi_language/rec_german_lite_train.yml)|2.65M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_train.tar) | -| korean_mobile_v2.0_rec | ppocr/utils/dict/korean_dict.txt |韩文识别|[rec_korean_lite_train.yml](../../configs/rec/multi_language/rec_korean_lite_train.yml)|3.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_train.tar) | -| japan_mobile_v2.0_rec | ppocr/utils/dict/japan_dict.txt |日文识别|[rec_japan_lite_train.yml](../../configs/rec/multi_language/rec_japan_lite_train.yml)|4.23M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_train.tar) | -| chinese_cht_mobile_v2.0_rec | ppocr/utils/dict/chinese_cht_dict.txt | 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) | -| te_mobile_v2.0_rec | ppocr/utils/dict/te_dict.txt | 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 | ppocr/utils/dict/ka_dict.txt |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) | -| ta_mobile_v2.0_rec | ppocr/utils/dict/ta_dict.txt |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) | -| latin_mobile_v2.0_rec | ppocr/utils/dict/latin_dict.txt | 拉丁文识别 | [rec_latin_lite_train.yml](../../configs/rec/multi_language/rec_latin_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_train.tar) | -| arabic_mobile_v2.0_rec | ppocr/utils/dict/arabic_dict.txt | 阿拉伯字母 | [rec_arabic_lite_train.yml](../../configs/rec/multi_language/rec_arabic_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_train.tar) | -| cyrillic_mobile_v2.0_rec | ppocr/utils/dict/cyrillic_dict.txt | 斯拉夫字母 | [rec_cyrillic_lite_train.yml](../../configs/rec/multi_language/rec_cyrillic_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_train.tar) | -| devanagari_mobile_v2.0_rec | ppocr/utils/dict/devanagari_dict.txt |梵文字母 | [rec_devanagari_lite_train.yml](../../configs/rec/multi_language/rec_devanagari_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_train.tar) | +| korean_PP-OCRv3_rec | ppocr/utils/dict/korean_dict.txt |韩文识别|[korean_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/korean_PP-OCRv3_rec.yml)|11M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_PP-OCRv3_rec_train.tar) | +| japan_PP-OCRv3_rec | ppocr/utils/dict/japan_dict.txt |日文识别|[japan_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/japan_PP-OCRv3_rec.yml)|11M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_PP-OCRv3_rec_train.tar) | +| chinese_cht_PP-OCRv3_rec | ppocr/utils/dict/chinese_cht_dict.txt | 中文繁体识别|[chinese_cht_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/chinese_cht_PP-OCRv3_rec.yml)|12M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_PP-OCRv3_rec_train.tar) | +| te_PP-OCRv3_rec | ppocr/utils/dict/te_dict.txt | 泰卢固文识别|[te_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/te_PP-OCRv3_rec.yml)|9.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_PP-OCRv3_rec_train.tar) | +| ka_PP-OCRv3_rec | ppocr/utils/dict/ka_dict.txt |卡纳达文识别|[ka_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/ka_PP-OCRv3_rec.yml)|9.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_PP-OCRv3_rec_train.tar) | +| ta_PP-OCRv3_rec | ppocr/utils/dict/ta_dict.txt |泰米尔文识别|[ta_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/ta_PP-OCRv3_rec.yml)|9.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_PP-OCRv3_rec_train.tar) | +| latin_PP-OCRv3_rec | ppocr/utils/dict/latin_dict.txt | 拉丁文识别 | [latin_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/latin_PP-OCRv3_rec.yml) |9.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_PP-OCRv3_rec_train.tar) | +| arabic_PP-OCRv3_rec | ppocr/utils/dict/arabic_dict.txt | 阿拉伯字母 | [arabic_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/rec_arabic_lite_train.yml) |9.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_PP-OCRv3_rec_train.tar) | +| cyrillic_PP-OCRv3_rec | ppocr/utils/dict/cyrillic_dict.txt | 斯拉夫字母 | [cyrillic_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/cyrillic_PP-OCRv3_rec.yml) |9.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_PP-OCRv3_rec_train.tar) | +| devanagari_PP-OCRv3_rec | ppocr/utils/dict/devanagari_dict.txt |梵文字母 | [devanagari_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/multi_language/devanagari_PP-OCRv3_rec.yml) |9.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_PP-OCRv3_rec_train.tar) | + 更多支持语种请参考: [多语言模型](./multi_languages.md)