ocrd-tool.json

{
  "git_url": "https://github.com/OCR-D/ocrd_keraslm",
  "version": "0.4.3",
  "tools": {
    "ocrd-keraslm-rate": {
      "executable": "ocrd-keraslm-rate",
      "categories": [
        "Text recognition and optimization"
      ],
      "steps": [
        "recognition/text-recognition"
      ],
      "description": "Rate elements of the text with a character-level LSTM language model in Keras",
      "input_file_grp": [
        "OCR-D-OCR-TESS",
        "OCR-D-OCR-KRAK",
        "OCR-D-OCR-OCRO",
        "OCR-D-OCR-CALA",
        "OCR-D-OCR-ANY",
        "OCR-D-COR-CIS",
        "OCR-D-COR-ASV"
      ],
      "output_file_grp": [
        "OCR-D-COR-LM"
      ],
      "parameters": {
        "model_file": {
          "type": "string",
          "format": "uri",
          "content-type": "application/x-hdf;subtype=bag",
          "description": "path of h5py weight/config file for model trained with keraslm",
          "required": true,
          "cacheable": true
        },
        "textequiv_level": {
          "type": "string",
          "enum": ["region", "line", "word", "glyph"],
          "default": "glyph",
          "description": "PAGE XML hierarchy level to evaluate TextEquiv sequences on"
        },
        "alternative_decoding": {
          "type": "boolean",
          "description": "whether to process all TextEquiv alternatives, finding the best path via beam search, and delete each non-best alternative",
          "default": true
        },
        "beam_width": {
          "type": "number",
          "format": "integer",
          "description": "maximum number of best partial paths to consider during search with alternative_decoding",
          "default": 10
        },
        "lm_weight": {
          "type": "number",
          "format": "float",
          "description": "share of the LM scores over the input confidences",
          "default": 0.5
        }
      },
      "resources": [
        {
          "url": "https://github.com/OCR-D/ocrd_keraslm/releases/download/v0.4.3/model_dta_full.h5",
          "name": "model_dta_full.h5",
          "description": "character-level LM as stateful contiguous LSTM model (2 layers, 128 hidden nodes each, window length 256) trained on complete Deutsches Textarchiv",
          "size": 1769684
        }
      ]
    }
  }
}