Global:
  use_gpu: true
  character_dict_path: /kaggle/input/custom-ocr-dataset/dict.txt
  save_model_dir: ./output/
  pretrained_model: /kaggle/working/PaddleOCR/pretrained_models/PP-OCRv5_server_rec_pretrained.pdparams

Architecture:
  model_type: rec
  algorithm: SVTR_HGNet
  Transform:
  Backbone:
    name: PPHGNetV2_B4
    text_rec: True
  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: 17

PostProcess:  
  name: CTCLabelDecode

Metric:
  name: RecMetric
  main_indicator: acc

Train:
  dataset:
    name: SimpleDataSet
    data_dir: /kaggle/input/custom-ocr-dataset
    label_file_list: 
      - /kaggle/input/custom-ocr-dataset/train.txt
  loader:
    batch_size_per_card: 16  # Уменьшите для экономии памяти
    num_workers: 2

Eval:
  dataset:
    name: SimpleDataSet
    data_dir: /kaggle/input/custom-ocr-dataset
    label_file_list:
      - /kaggle/input/custom-ocr-dataset/val.txt
    transforms:
    - DecodeImage:
        img_mode: BGR
        channel_first: false
    - MultiLabelEncode:
        gtc_encode: NRTRLabelEncode
        max_text_length: 17
    - 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