🐛 bug fix on OCR generation

alan-turing-institute · Dec 6, 2024 · 3f6c10d · 3f6c10d
1 parent ad634b2
commit 3f6c10d
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/src/arc_spice/data/multieurlex_utils.py b/src/arc_spice/data/multieurlex_utils.py
@@ -67,7 +67,7 @@ def extract_articles(
 
 def _make_ocr_data(text: str) -> list[tuple[Image.Image, str]]:
     text_split = text.split()
-    text_split = [text for text in text_split if text not in ("", " ")]
+    text_split = [text for text in text_split if text not in ("", " ", None)]
     generator = GeneratorFromStrings(text_split, count=len(text_split))
     return list(generator)