yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-10-13 09:12:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix

Browse Source
This commit is contained in:
Jake Poznanski 2025-03-19 18:33:48 +00:00
parent a4605e4efc
commit cb4dfeba36
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
olmocr/bench/tests.py
View File

@ -38,6 +38,9 @@ class ValidationError(Exception):
def normalize_text(md_content: str) -> str:
if md_content is None:
return None
# Normalize whitespace in the md_content
md_content = re.sub(r"\s+", " ", md_content)