.

src/eynollah/eynollah_ocr.py

@@ -72,7 +72,7 @@ class Eynollah_ocr:
             self.model_zoo.load_model('ocr', '')
             self.model_zoo.load_model('num_to_char')
             self.model_zoo.load_model('characters')
-            self.end_character = len(self.model_zoo.get('characters', list)) + 2
+            self.end_character = len(self.model_zoo.get('characters')) + 2
 
     @property
     def device(self):

src/eynollah/model_zoo/model_zoo.py

@@ -197,9 +197,12 @@ class EynollahModelZoo:
         return model
 
     def get(self, model_category: str) -> Predictor:
-        if model_category not in self._loaded:
+        # if model_category not in self._loaded:
-            raise ValueError(f'Model "{model_category}" not previously loaded with "load_model(..)"')
+        #     raise ValueError(f'Model "{model_category}" not previously loaded with "load_model(..)"')
-        return self._loaded[model_category]
+        if model_category in self._loaded:
+            return self._loaded[model_category]
+        else:
+            return self.load_model(model_category)
 
     def _load_ocr_model(self, variant: str) -> AnyModel:
         """

src/eynollah/ocrd-tool.json

@@ -162,43 +162,50 @@
           "version_range": "< v0.7.0"
         }
       ]
-    }
-  },
-  "ocrd-eynollah-recognize": {
-    "executable": "ocrd-eynollah-recognize",
-    "categories": ["Text recognition and optimization"],
-    "steps": ["recognition/text-recognition"],
-    "input_file_grp_cardinality": 1,
-    "output_file_grp_cardinality": 1,
-    "parameters": {
-      "models": {
-        "type": "string",
-        "format": "uri",
-        "content-type": "text/directory",
-        "cacheable": true,
-        "description": "Directory containing the eynollah_models directory",
-        "required": true
-      },
-      "do_not_mask_with_textline_contour": {
-        "type": "boolean",
-        "description": "if this parameter set to true, cropped textline images will not be masked with textline contour.",
-        "default": false
-      },
-      "tr_ocr": {
-        "type": "boolean",
-        "description": "Whether to use (much more resource-intensive) transformer model",
-        "default": false
-      }
     },
-    "resources": [
+    "ocrd-eynollah-recognize": {
-      {
+      "executable": "ocrd-eynollah-recognize",
-        "url": "https://zenodo.org/records/17580627/files/models_ocr_v0_6_0.tar.gz?download=1",
+      "categories": ["Text recognition and optimization"],
-        "name": "models_ocr_v0_6_0",
+      "steps": ["recognition/text-recognition"],
-        "type": "archive",
+      "input_file_grp_cardinality": 1,
-        "size": 6119874002,
+      "output_file_grp_cardinality": 1,
-        "description": "Models for OCR",
+      "description": "Recognize text with eynollah (CNN/RNN or Transformer)",
-        "version_range": ">= v0.6.0"
+      "parameters": {
-      }
+        "models": {
-    ]
+          "type": "string",
+          "format": "uri",
+          "content-type": "text/directory",
+          "cacheable": true,
+          "description": "Directory containing the eynollah_models directory",
+          "required": true
+        },
+        "do_not_mask_with_textline_contour": {
+          "type": "boolean",
+          "description": "if this parameter set to true, cropped textline images will not be masked with textline contour.",
+          "default": false
+        },
+        "tr_ocr": {
+          "type": "boolean",
+          "description": "Whether to use (much more resource-intensive) transformer model",
+          "default": false
+        },
+	"batch_size": {
+	  "type": "number",
+	  "format": "integer",
+	  "description": "Batch size, leave as 0 for builtin default (2 for CNN/RNN, 2 for TrOCR)",
+	  "default": 0
+	}
+      },
+      "resources": [
+        {
+          "url": "https://zenodo.org/records/17580627/files/models_ocr_v0_6_0.tar.gz?download=1",
+          "name": "models_ocr_v0_6_0",
+          "type": "archive",
+          "size": 6119874002,
+          "description": "Models for OCR",
+          "version_range": ">= v0.6.0"
+        }
+      ]
+    }
   }
 }

src/eynollah/ocrd_cli_recognize.py

@@ -34,8 +34,8 @@ class EynollahRecognizeProcessor(Processor):
             model_zoo=model_zoo,
             tr_ocr=self.parameter['tr_ocr'],
             do_not_mask_with_textline_contour=self.parameter['do_not_mask_with_textline_contour'],
-            batch_size=self.parameter['batch_size'],
+            batch_size=self.parameter['batch_size'] if self.parameter['batch_size'] >= 0 else 2 if self.parameter['tr_ocr'] else 8,
-            min_conf_value_of_textline_text=self.parameter['min_conf_value_of_textline_text'])
+            min_conf_value_of_textline_text=0)
 
     # FIXME: This is just a proof-of-concept, very inefficient and non-conformant
     # TODO: OCR writing should use PAGE API once result dataclass mechanism is settled,