{"slug":"indra-ocr","name":"Indra OCR","nameZh":"Indra OCR（Datalab 1M 参数 CPU OCR）","category":"rag-docs","categoryName":"Document parsing & web scraping","audience":["for-ai"],"primary":"for-ai","openClosed":"open","pricing":"open-source","license":"OpenRAIL-M","maintained":"yes","officialUrl":"https://huggingface.co/datalab-to/indra-ocr","repo":null,"latestVersion":null,"latestRelease":null,"stars":null,"starsAsOf":null,"description":"A ~1M-parameter OCR model from Datalab (makers of Marker / Surya) that runs on CPU via ONNX Runtime: PDFs and images to Markdown, text or JSON with boxes, 80+ languages, handwriting and rotated pages, with layout blocks and reading order. Benchmarks are vendor-reported; model OpenRAIL-M, code Apache-2.0","descriptionZh":"Datalab（Marker / Surya 作者）发布的约 100 万参数 OCR 模型，只用 ONNX Runtime 在 CPU 上跑：把 PDF 和图片转成 Markdown、文本或带框 JSON，支持 80 多种语言、手写和任意角度页面，并给出版面块和阅读顺序。性能数字为厂商自述；模型 OpenRAIL-M，代码 Apache-2.0","callMethods":[],"platforms":[],"addedAt":"2026-10-21","updatedAt":null,"topics":[],"language":null,"lastPush":null,"formerly":null,"packages":[],"recentVersions":[],"alternatives":["firecrawl","markitdown","ragflow","paddleocr","crawl4ai","mineru","docling","pandoc"],"stacks":[],"scenarios":["rag-and-documents"],"problems":[],"reasonZh":null,"sources":["editorial"],"record":"https://aimap.page/api/v1/software/indra-ocr.json","pages":{"en":"https://aimap.page/en/software/indra-ocr/","zh-hans":"https://aimap.page/zh-hans/software/indra-ocr/"}}