hotfixes

config/pipeline.development.yaml

@@ -3,10 +3,10 @@ debug: true
 
 # Processing settings
 processing:
-  batch_size: 10_000
+  batch_size: 100_000
-  max_workers: 8
+  max_workers: 1
   checkpoint_interval: 10
-  use_multiprocessing: true
+  use_multiprocessing: false
 
 # Pipeline stages
 stages:

processing/ner/formats/connectors_format.py

@@ -12,6 +12,7 @@ class ConnectorFormatter(BaseNameFormatter):
         surname = row['probable_surname'] if pd.notna(row['probable_surname']) else ''
         connector = random.choice(self.connectors)
 
+        # Connect native parts with a random connector
         if len(native_parts) > 1:
             connected_native = f" {connector} ".join(native_parts)
             full_name = f"{connected_native} {surname}".strip()