Indra OCR open-sourced: 18MB ONNX model, pip install, 14 languages
VikParuchuri · x · 2026-10-14
Follow-up from Vik Paruchuri with links for Indra OCR: Hugging Face weights (datalab-to/indra-ocr, openrail, 18MB ONNX, no PyTorch), code, and blog post. Usage is pip install indra-ocr then indra-ocr paper.pdf, outputting markdown, plain text, or JSON with boxes; 14 languages, 230ms/page on 4 vCPUs, reads digital PDF text layers and OCRs only gaps. Datalab also pitches its managed high-accuracy model Chandra and batch service.
More from Models
- DeepSeek ships V4.1-Flash-1017: open weights, 1M context, claims Opus 5-level coding — CurieuxExplorer · 2026-10-17
- Elorian launches Glimpse, an Astra-level visual reasoning model at 17x lower cost — CurieuxExplorer · 2026-10-17
- Reflection AI open-sources Beam weights under Apache 2.0 with Mirror CLI harness — CurieuxExplorer · 2026-10-17
- Generative UI 101: Building Live Interfaces with Agents on Opus 5.5 and Rivals — EXM7777 · 2026-10-17
- OpenAI's new $500 tier and $200 plan throttling are driving power users away — cybrstg · 2026-10-17
- DeepSeek shows rapid vision gains: agent self-checks screenshots to build 3D scene — cedric_chee · 2026-10-17