feat: enhance logging and memory management across modules

2025-08-13 23:09:05 +02:00
parent 47e52d130c
commit 9601c5e44d
48 changed files with 1004 additions and 773 deletions
@@ -64,6 +64,7 @@ data:
    ner_spacy: "names_ner.spacy"            # Output file for NER annotated data using spaCy format
  split_evaluation: false                   # Should the dataset be split into training and evaluation sets ?
  split_by_gender: true                     # Should the dataset be split by gender ?
+  split_by_province: true                   # Should the dataset be split by province ?
  split_ner_data: true                      # Should the NER data be extracted and saved?
  evaluation_fraction: 0.2                  # Fraction of data to use for evaluation
  random_seed: 42                           # Random seed for reproducibility