nemotron-ocr

Model Overview

Description

Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images. It integrates three core neural network modules: a detector for text region localization, a recognizer for transcription of detected regions, and a relational model for layout and structure analysis.

This model is optimized for a wide variety of OCR tasks, including multi-line, multi-block, and natural scene text, and it supports advanced reading order analysis via its relational model component. Nemotron OCR v2 supports multiple languages and has been developed to be production-ready and commercially usable, with a focus on speed and accuracy on both document and natural scene images.

Nemotron OCR v2 is part of the NVIDIA NeMo Retriever collection, which provides state-of-the-art, commercially-ready models and microservices optimized for the lowest latency and highest throughput. It features a production-ready information retrieval pipeline with enterprise support. The models that form the core of this solution have been trained using responsibly selected, auditable data sources. With multiple pre-trained models available as starting points, developers can readily customize them for domain-specific use cases, such as information technology, human resource help assistants, and research and development assistants.

This model is ready for commercial use.

License/Terms of use

The model is governed by the NVIDIA Open Model License Agreement. Additional Information:Apache 2.0

Release Date:

Hugging Face (this repo): nvidia/nemotron-ocr-v2 Build.Nvidia.com 04/15/2026 via https://build.nvidia.com/nvidia/nemotron-ocr-v2 NGC 04/15/2026 via https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo-microservices/containers/nemoretriever-ocr-v2

Deployment Geography

Global

Use Case

Nemotron OCR v2 is designed for high-accuracy and high-speed extraction of textual information from images across multiple languages, making it ideal for powering multimodal retrieval systems, Retrieval-Augmented Generation (RAG) pipelines, and agentic applications that require seamless integration of visual and language understanding. Its robust multilingual performance and efficiency make it an excellent choice for next-generation AI systems that demand both precision and scalability across diverse real-world content.

Model Architecture

Architecture Type: Hybrid detector-recognizer with document-level relational modeling

Nemotron OCR v2 is available in two variants:

• v2_english — Optimized for English-language OCR with word-level region handling.
• v2_multilingual — Supports English, Chinese (Simplified and Traditional), Japanese, Korean, and Russian with line-level region handling for multilingual documents.

Both variants share the same three-component architecture:

• Text Detector: Utilizes a RegNetX-8GF convolutional backbone for high-accuracy localization of text regions within images.
• Text Recognizer: Employs a pre-norm Transformer-based sequence recognizer to transcribe text from detected regions, supporting variable word and line lengths.
• Relational Model: Applies a multi-layer global relational module to predict logical groupings, reading order, and layout relationships across detected text elements.

All components are trained jointly in an end-to-end fashion, providing robust, scalable, and production-ready OCR for diverse document and scene images.

Network Architecture: RegNetX-8GF

Recognizer Comparison

The two variants share an identical detector and relational architecture but differ in recognizer capacity:

Parameter Counts

v2_english (from v2_english/):

v2_multilingual (from v2_multilingual/):

Input

Output