--- title: Building a Fast Multilingual OCR Model with Synthetic Data description: NVIDIA released Nemotron OCR v2, a multilingual OCR model trained on 12.2 million synthetic images across six languages (English, Japanese, Korean, Russian,... canonical: https://daily.dev/posts/building-a-fast-multilingual-ocr-model-with-synthetic-data-tuii4mnwu twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Building a Fast Multilingual OCR Model with Synthetic Data | daily.dev og:description: NVIDIA released Nemotron OCR v2, a multilingual OCR model trained on 12.2 million synthetic images across six languages (English, Japanese, Korean, Russian,... og:url: https://daily.dev/posts/building-a-fast-multilingual-ocr-model-with-synthetic-data-tuii4mnwu og:image: https://api.daily.dev/og/posts/TUii4mnWu.png og:image:alt: Building a Fast Multilingual OCR Model with Synthetic Data og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Building a Fast Multilingual OCR Model with Synthetic Data **[Hugging Face](https://daily.dev/sources/huggingface)** · 10 min read · 0 upvotes · 0 comments ## Summary NVIDIA released Nemotron OCR v2, a multilingual OCR model trained on 12.2 million synthetic images across six languages (English, Japanese, Korean, Russian, Simplified and Traditional Chinese). The synthetic data pipeline, built on a modified SynthDoG renderer, generates pixel-perfect annotations at word, line, and paragraph levels with reading order graphs, using mOSCAR for source text and open-source font pools. The model uses a FOTS-inspired shared backbone architecture that reuses feature maps across detection, recognition, and relational components, achieving 34.7 pages/second on a single A100 GPU. NED scores for non-English languages dropped from 0.56–0.92 (v1) to 0.035–0.069 (v2), outperforming specialized per-language models like PaddleOCR. The dataset and model are publicly available on Hugging Face. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent](https://daily.dev/posts/how-to-fine-tune-nemotron-3-5-asr-for-your-language-domain-or-accent-lmayxxp44) · Hugging Face · 0 upvotes · 0 comments - [Run Multimodal Reasoning Agents with NVIDIA Nemotron on vLLM](https://daily.dev/posts/run-multimodal-reasoning-agents-with-nvidia-nemotron-on-vllm-vumht6rln) · vLLM · 0 upvotes · 0 comments - [Nvidia’s best model is now live](https://daily.dev/posts/nvidia-s-best-model-is-now-live-tsagrzqp8) · The New Stack · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#nvidia](https://daily.dev/tags/nvidia), [#computer-vision](https://daily.dev/tags/computer-vision) [View this post on daily.dev](https://daily.dev/posts/building-a-fast-multilingual-ocr-model-with-synthetic-data-tuii4mnwu) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Building a Fast Multilingual OCR Model with Synthetic Data","url":"https://daily.dev/posts/building-a-fast-multilingual-ocr-model-with-synthetic-data-tuii4mnwu","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/building-a-fast-multilingual-ocr-model-with-synthetic-data-tuii4mnwu"},"datePublished":"2026-04-20T13:19:38.907Z","dateModified":"2026-04-20T13:23:10.653Z","description":"NVIDIA released Nemotron OCR v2, a multilingual OCR model trained on 12.2 million synthetic images across six languages (English, Japanese, Korean, Russian,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/196e20b940be640cca91f9df292d01b8?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/196e20b940be640cca91f9df292d01b8?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hugging Face","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hugging Face","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f1f55c67d81a4330acf5b90b26b0c8e1","url":"https://daily.dev/sources/huggingface"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/building-a-fast-multilingual-ocr-model-with-synthetic-data-tuii4mnwu","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,nvidia,computer-vision","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hugging Face","item":"https://daily.dev/sources/huggingface"},{"@type":"ListItem","position":3,"name":"Building a Fast Multilingual OCR Model with Synthetic Data"}]} ```