add ppocrv3 for multilingualism (#2663)

* add ppocrv3 for multilingualism

* change config path

paddlex/configs/modules/text_recognition/PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_001.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/PP-OCRv4_server_rec_doc.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: PP-OCRv4_server_rec_doc
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_rec_doc_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_rec_doc_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_001.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/arabic_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: arabic_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/arabic_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/arabic_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_010_arabic.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/chinese_cht_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: chinese_cht_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/chinese_cht_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/chinese_cht_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_005_chinese_cht.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/cyrillic_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: cyrillic_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/cyrillic_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/cyrillic_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_011_cyrillic.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/devanagari_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: devanagari_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/devanagari_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/devanagari_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_012_devanagari.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/en_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: en_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/en_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/en_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_002_en.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/en_PP-OCRv4_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: en_PP-OCRv4_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/en_PP-OCRv4_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/en_PP-OCRv4_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_002_en.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/japan_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: japan_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/japan_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/japan_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_004_japan.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/ka_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: ka_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ka_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ka_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_007_ka.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/korean_PP-OCRv3_mobile_rec.yml

@@ -0,0 +1,39 @@
+Global:
+  model: korean_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/korean_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/korean_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_003_korean.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/latin_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: latin_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/latin_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/latin_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_009_latin.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/ta_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: ta_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ta_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ta_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_008_ta.png"
+  kernel_option:
+    run_mode: paddle

paddlex/configs/modules/text_recognition/te_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,39 @@
+Global:
+  model: te_PP-OCRv3_mobile_rec
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/ocr_rec/ocr_rec_dataset_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  epochs_iters: 20
+  batch_size: 8
+  learning_rate: 0.001
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/te_PP-OCRv3_mobile_rec_pretrained.pdparams
+  resume_path: null
+  log_interval: 20
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_accuracy/best_accuracy.pdparams"
+  log_interval: 1
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/te_PP-OCRv3_mobile_rec_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_accuracy/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_006_te.png"
+  kernel_option:
+    run_mode: paddle

paddlex/inference/utils/official_models.py

@@ -193,6 +193,34 @@ PP-OCRv4_server_rec_infer.tar",
     "Cascade-MaskRCNN-ResNet50-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/Cascade-MaskRCNN-ResNet50-FPN_infer.tar",
     "Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN_infer.tar",
     "PP-YOLOE_seg-S": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-YOLOE_seg-S_infer.tar",
+    "PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+PP-OCRv3_mobile_rec_infer.tar",
+    "en_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+en_PP-OCRv3_mobile_rec_infer.tar",
+    "korean_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+korean_PP-OCRv3_mobile_rec_infer.tar",
+    "japan_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+japan_PP-OCRv3_mobile_rec_infer.tar",
+    "chinese_cht_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+chinese_cht_PP-OCRv3_mobile_rec_infer.tar",
+    "te_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+te_PP-OCRv3_mobile_rec_infer.tar",
+    "ka_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+ka_PP-OCRv3_mobile_rec_infer.tar",
+    "ta_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+ta_PP-OCRv3_mobile_rec_infer.tar",
+    "latin_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+latin_PP-OCRv3_mobile_rec_infer.tar",
+    "arabic_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+arabic_PP-OCRv3_mobile_rec_infer.tar",
+    "cyrillic_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+cyrillic_PP-OCRv3_mobile_rec_infer.tar",
+    "devanagari_PP-OCRv3_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+devanagari_PP-OCRv3_mobile_rec_infer.tar",
+    "en_PP-OCRv4_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+en_PP-OCRv4_mobile_rec_infer.tar",
+    "PP-OCRv4_server_rec_doc": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
+PP-OCRv4_server_rec_doc_infer.tar",
     "PP-OCRv4_mobile_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
 PP-OCRv4_mobile_rec_infer.tar",
     "PP-OCRv4_server_det": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\

paddlex/modules/text_recognition/evaluator.py

@@ -35,6 +35,10 @@ class TextRecEvaluator(BaseEvaluator):
             self.pdx_config.update_dataset(
                 self.global_config.dataset_dir, "LaTeXOCRDataSet"
             )
+        elif "PP-OCRv3" in self.global_config["model"]:
+            self.pdx_config.update_dataset(
+                self.global_config.dataset_dir, "SimpleDataSet"
+            )
         else:
             self.pdx_config.update_dataset(
                 self.global_config.dataset_dir, "MSTextRecDataset"

paddlex/modules/text_recognition/model_list.py

@@ -13,8 +13,22 @@
 # limitations under the License.
 
 MODELS = [
+    "PP-OCRv3_mobile_rec",
+    "en_PP-OCRv3_mobile_rec",
+    "korean_PP-OCRv3_mobile_rec",
+    "japan_PP-OCRv3_mobile_rec",
+    "chinese_cht_PP-OCRv3_mobile_rec",
+    "te_PP-OCRv3_mobile_rec",
+    "ka_PP-OCRv3_mobile_rec",
+    "ta_PP-OCRv3_mobile_rec",
+    "latin_PP-OCRv3_mobile_rec",
+    "arabic_PP-OCRv3_mobile_rec",
+    "cyrillic_PP-OCRv3_mobile_rec",
+    "devanagari_PP-OCRv3_mobile_rec",
     "PP-OCRv4_mobile_rec",
     "PP-OCRv4_server_rec",
+    "en_PP-OCRv4_mobile_rec",
+    "PP-OCRv4_server_rec_doc",
     "ch_SVTRv2_rec",
     "ch_RepSVTR_rec",
 ]

paddlex/modules/text_recognition/trainer.py

@@ -54,6 +54,10 @@ class TextRecTrainer(BaseTrainer):
             self.pdx_config.update_dataset(
                 self.global_config.dataset_dir, "LaTeXOCRDataSet"
             )
+        elif "PP-OCRv3" in self.global_config["model"]:
+            self.pdx_config.update_dataset(
+                self.global_config.dataset_dir, "SimpleDataSet"
+            )
         else:
             self.pdx_config.update_dataset(
                 self.global_config.dataset_dir, "MSTextRecDataset"

paddlex/repo_apis/PaddleOCR_api/configs/PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,133 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v3
+  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/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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]
+        max_text_length: *max_text_length
+    - 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

paddlex/repo_apis/PaddleOCR_api/configs/PP-OCRv4_server_rec_doc.yaml

@@ -0,0 +1,137 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 20
+  save_model_dir: ./output/rec_ppocr_v4_hgnet_doc
+  save_epoch_step: 10
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/ch_PP-OCRv4_rec_server_trained.pdparams
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.txt
+  d2s_train_image_shape: [3,48,320]
+
+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_HGNet
+  Transform:
+  Backbone:
+    name: PPHGNet_small
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: MSTextRecDataset
+    ds_width: false
+    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]
+        max_text_length: *max_text_length
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: 8
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: 8
+    drop_last: true
+    num_workers: 8
+Eval:
+  dataset:
+    name: TextRecDataset
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

paddlex/repo_apis/PaddleOCR_api/configs/arabic_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,132 @@
+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/arabic/ar_2.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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/configs/chinese_cht_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,132 @@
+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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/configs/cyrillic_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,132 @@
+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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/configs/devanagari_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,132 @@
+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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/configs/en_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,134 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_en_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/en_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_en.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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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
+    ds_width: false
+    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]
+        max_text_length: *max_text_length
+    - 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: 0
+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: 0

paddlex/repo_apis/PaddleOCR_api/configs/en_PP-OCRv4_mobile_rec.yaml

@@ -0,0 +1,150 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 50
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v4
+  save_epoch_step: 10
+  eval_batch_step:
+  - 0
+  - 2000
+  cal_metric_during_train: true
+  pretrained_model: null
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/en_dict.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.txt
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.0005
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+Architecture:
+  model_type: rec
+  algorithm: SVTR_LCNet
+  Transform: null
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.95
+  Head:
+    name: MultiHead
+    head_list:
+    - CTCHead:
+        Neck:
+          name: svtr
+          dims: 120
+          depth: 2
+          hidden_dims: 120
+          kernel_size:
+          - 1
+          - 3
+          use_guide: true
+        Head:
+          fc_decay: 1.0e-05
+    - NRTRHead:
+        nrtr_dim: 384
+        max_text_length: 25
+Loss:
+  name: MultiLoss
+  loss_config_list:
+  - CTCLoss: null
+  - NRTRLoss: null
+PostProcess:
+  name: CTCLabelDecode
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: false
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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
+        max_text_length: 25
+    - RecAug: null
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales:
+    - - 320
+      - 32
+    - - 320
+      - 48
+    - - 320
+      - 64
+    first_bs: 96
+    fix_bs: false
+    divided_factor:
+    - 8
+    - 16
+    is_training: true
+  loader:
+    shuffle: true
+    batch_size_per_card: 96
+    drop_last: true
+    num_workers: 8
+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:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape:
+        - 3
+        - 48
+        - 320
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4
+profiler_options: null

paddlex/repo_apis/PaddleOCR_api/configs/japan_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,132 @@
+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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/configs/ka_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,132 @@
+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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/configs/korean_PP-OCRv3_mobile_rec.yml

@@ -0,0 +1,132 @@
+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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/configs/latin_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,132 @@
+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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/configs/ta_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,132 @@
+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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/configs/te_PP-OCRv3_mobile_rec.yaml

@@ -0,0 +1,132 @@
+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_LCNet
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+    last_pool_kernel_size: [2, 2]
+  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

paddlex/repo_apis/PaddleOCR_api/text_rec/config.py

@@ -91,6 +91,17 @@ class TextRecConfig(BaseConfig):
                 "Global.character_dict_path": os.path.join(dataset_path, "dict.txt"),
             }
             self.update(_cfg)
+        elif dataset_type == "SimpleDataSet":
+            _cfg = {
+                "Train.dataset.name": dataset_type,
+                "Train.dataset.data_dir": dataset_path,
+                "Train.dataset.label_file_list": [train_list_path],
+                "Eval.dataset.name": "SimpleDataSet",
+                "Eval.dataset.data_dir": dataset_path,
+                "Eval.dataset.label_file_list": [os.path.join(dataset_path, "val.txt")],
+                "Global.character_dict_path": os.path.join(dataset_path, "dict.txt"),
+            }
+            self.update(_cfg)
         elif dataset_type == "LaTeXOCRDataSet":
             _cfg = {
                 "Train.dataset.name": dataset_type,

paddlex/repo_apis/PaddleOCR_api/text_rec/register.py

@@ -36,6 +36,116 @@ register_suite_info(
 
 register_model_info(
     {
+        "model_name": "PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "en_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "en_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+
+register_model_info(
+    {
+        "model_name": "korean_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "korean_PP-OCRv3_mobile_rec.yml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "japan_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "japan_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "chinese_cht_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "chinese_cht_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "te_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "te_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "ka_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "ka_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "ta_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "ta_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "latin_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "latin_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "arabic_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "arabic_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "cyrillic_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "cyrillic_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "devanagari_PP-OCRv3_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "devanagari_PP-OCRv3_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+
+register_model_info(
+    {
         "model_name": "PP-OCRv4_mobile_rec",
         "suite": "TextRec",
         "config_path": osp.join(PDX_CONFIG_DIR, "PP-OCRv4_mobile_rec.yaml"),
@@ -54,6 +164,24 @@ register_model_info(
 
 register_model_info(
     {
+        "model_name": "en_PP-OCRv4_mobile_rec",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "en_PP-OCRv4_mobile_rec.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
+        "model_name": "PP-OCRv4_server_rec_doc",
+        "suite": "TextRec",
+        "config_path": osp.join(PDX_CONFIG_DIR, "PP-OCRv4_server_rec_doc.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+    }
+)
+
+register_model_info(
+    {
         "model_name": "ch_SVTRv2_rec",
         "suite": "TextRec",
         "config_path": osp.join(PDX_CONFIG_DIR, "ch_SVTRv2_rec.yaml"),