Ir para o conteúdo
ModelListadosExterno
Baixar

Nemotron Ocr v2

nvidia-open-model-license

TipoOtherVersãoRevision 3196cb5Cnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
8,63–174 MB
Versão
vRevision 3196cb5
Atualizado
14 de set. de 2026
Downloads
7
Fonte
Hugging Face

Trecho da fonte

nvidia-open-model-license

Fontes

1 fonte
Hugging FacePrimárioVersão 3196cb59376554354063224543b3f1396f5ea118
huggingface.co/Albert2999/nemotron-ocr-v2/tree/3196cb59376554354063224543b3f1396f5ea118

Verificado 20 de ago.

Artefatos de modelo

6 artefatos

v2_english/detector.pth

pth · 174 MB · SHA-256 064950b56583…2d2b · Hugging Face

Baixar

v2_english/recognizer.pth

pth · 23,4 MB · SHA-256 366af771f46b…f728 · Hugging Face

Baixar

v2_english/relational.pth

pth · 8,63 MB · SHA-256 763c18416f8b…3816 · Hugging Face

Baixar

v2_multilingual/detector.pth

pth · 174 MB · SHA-256 d54398ec3915…42e9 · Hugging Face

Baixar

v2_multilingual/recognizer.pth

pth · 138 MB · SHA-256 20bf070ab5d9…647c · Hugging Face

Baixar

v2_multilingual/relational.pth

pth · 8,75 MB · SHA-256 509701e97de0…e10b · Hugging Face

Baixar

Trechos de fonte

2 trechos

--- license: other license_name: nvidia-open-model-license license_link: >- https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ language: - en - zh - ja - ko - ru pipeline_tag: image-to-text arxiv: None tags: - image - ocr - object recognition - text recognition - layout analysis - ingestion - multilingual --- # Nemotron OCR v2 ## **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 use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) and the use of the post-processing scripts are licensed under [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt). ### Release Date: <br> Hugging Face (this repo): [nvidia/nemotron-ocr-v2](https://huggingface.co/nvidia/nemotron-ocr-v2) <br> Build.Nvidia.com 04/15/2026 via [https://build.nvidia.com/nvidia/nemotron-ocr-v2](https:...

Source context: 7 downloads · 0 likes · Pipeline image-to-text · Repo Albert2999/nemotron-ocr-v2