yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-06-27 04:00:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding more workers by default to improve bench perf

Browse Source
This commit is contained in:
Jake Poznanski 2025-06-13 03:50:21 +00:00
parent 43c94fea58
commit cc0c62ab73
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
olmocr/pipeline.py
View File

@ -975,7 +975,7 @@ async def main():
parser.add_argument("--pages_per_group", type=int, default=500, help="Aiming for this many pdf pages per work item group")
parser.add_argument("--max_page_retries", type=int, default=8, help="Max number of times we will retry rendering a page")
parser.add_argument("--max_page_error_rate", type=float, default=0.004, help="Rate of allowable failed pages in a document, 1/250 by default")
parser.add_argument("--workers", type=int, default=8, help="Number of workers to run at a time")
parser.add_argument("--workers", type=int, default=20, help="Number of workers to run at a time")
parser.add_argument("--apply_filter", action="store_true", help="Apply basic filtering to English pdfs which are not forms, and not likely seo spam")
parser.add_argument("--stats", action="store_true", help="Instead of running any job, reports some statistics about the current workspace")
parser.add_argument("--markdown", action="store_true", help="Also write natural text to markdown files preserving the folder structure of the input pdfs")