Datalab releases Indra, a low-latency CPU OCR model with 60-language and math support
VikParuchuri · x · 2026-10-14
Datalab founder Vik Paruchuri released Indra, a small OCR model built for low latency on CPU, aimed at RAG ingestion, search indexing, and triage before larger models.
- Supports 60 languages and 6 scripts (Latin, Cyrillic, Greek, Devanagari, Bengali, Chinese), plus any script from a PDF text layer
- Handles math via a dedicated math mode
- Limitations: handwriting, complex tables, and large pages may fail — the company points users to Chandra OCR 2 for those
- Model weights, code, and blog post are all publicly available
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