Add pre-NMS centerness + peak filter for faster inference

updated readme.md

fix missing runtime/build deps and add Slurm helper scriptspyproject.toml: add numpy, huggingface_hub to dependencies andeditables to build-system.requires so editable installs workcleanly without manual workarounds.New scripts:- submit_install_gpu.sh: GPU-node venv creation + package build- submit_inference_viz_gpu.sh: GPU-node batched v2 inference + viz- run_ocr_inference.py: directory-level inference with JSON output

Upload config.json

removed blank config.json

updated model card

merged english and multilingual and updated model card

Duplicate from nvidia/nemotron-ocr-v2-multilingual