yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-11-09 06:59:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Actually install the right thing

Browse Source
This commit is contained in:
Jake Poznanski 2025-06-12 21:18:58 +00:00
parent 548187902b
commit 4bfcfce767
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/run_marker_benchmark.sh
View File

@ -96,7 +96,7 @@ if has_aws_creds:
commands.extend([ commands.extend([
"git clone https://huggingface.co/datasets/allenai/olmOCR-bench", "git clone https://huggingface.co/datasets/allenai/olmOCR-bench",
"cd olmOCR-bench && git lfs pull && cd ..", "cd olmOCR-bench && git lfs pull && cd ..",
f"pip install marker=={marker_version}", f"pip install marker-pdf=={marker_version}",
"python -m olmocr.bench.convert marker --dir ./olmOCR-bench/bench_data", "python -m olmocr.bench.convert marker --dir ./olmOCR-bench/bench_data",
"python -m olmocr.bench.benchmark --dir ./olmOCR-bench/bench_data" "python -m olmocr.bench.benchmark --dir ./olmOCR-bench/bench_data"
]) ])
@ -146,7 +146,7 @@ if has_aws_creds:
'echo "$AWS_CREDENTIALS_FILE" > ~/.aws/credentials' 'echo "$AWS_CREDENTIALS_FILE" > ~/.aws/credentials'
]) ])
perf_commands.extend([ perf_commands.extend([
f"pip install marker=={marker_version}", f"pip install marker-pdf=={marker_version}",
"s5cmd cp s3://ai2-oe-data/jakep/olmocr/olmOCR-mix-0225/benchmark_set/* /root/olmOCR-mix-0225_benchmark_set/", "s5cmd cp s3://ai2-oe-data/jakep/olmocr/olmOCR-mix-0225/benchmark_set/* /root/olmOCR-mix-0225_benchmark_set/",
"marker --force_ocr /root/olmOCR-mix-0225_benchmark_set/ --output_dir /root/olmOCR-mix-0225_benchmark_set_marker --workers 8" "marker --force_ocr /root/olmOCR-mix-0225_benchmark_set/ --output_dir /root/olmOCR-mix-0225_benchmark_set_marker --workers 8"
]) ])