TeleOCR — China Telecom's 1.2B open-source document parsing model
A ~1.2B open-source document parsing model from China Telecom's Xingchen AGI Lab; unifies digital and camera-captured document parsing into structured outputs (Markdown, tables, formulas); HF trending with 30.4k downloads.
Why it matters
A photographed contract parsed as accurately as a clean PDF — unifying digital + camera-captured documents in a lightweight 1.2B model.
What you could build with it
A document-automation team can use TeleOCR to convert photographed/scanned contracts and forms into structured markdown for RAG ingestion; an indie hacker can ship a mobile document-scanner with structured export.
Does it hold up?
Early traction: 30.4k HF downloads in ~2 days; the independent OmniDocBench leaderboard confirms its top scores. Other claims remain company-issued.
Built with TeleOCR
- China Telecom Unveils TeleOCR: Lightweight 1.2B Model Tops Global Document Parsing Benchmarksindiaeveningpost · Announcement coverage: open-source 1.2B model from Xingchen AGI Lab unifying digital and camera-captured document parsing.
- OmniDocBench — third-party benchmark leaderboard including TeleOCRgithub · Third-party benchmark repo whose published README leaderboard includes TeleOCR's OmniDocBench v1.6 results (96.91 overall, top of the specialized-VLM table) — independent confirmation of the claimed scores.
Learn more
First spotted on hf: source.
More AI models
ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languagesVoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video…models · JEV 0.71DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69Mistral Forge: enterprise platform for training and continuously improving proprietary modelsMistral AI launched Forge (Sep 28) — a full-lifecycle model training platform (pre-training, SFT, DPO/ODPO, RL…models · JEV 0.69kev: open, trainable Jev-like family of small decision models on Qwen3.5/3.8A family of small decision models (0.8B to 27B) built on Qwen3.5/3.8 that reproduces Jev's prefill-only typed-decision…models · JEV 0.68GPT-Synopsys: OpenAI and Synopsys multi-year deal to build an AI model that operates EDA toolsOpenAI and Synopsys signed a multi-year agreement on Sep 30 to jointly develop GPT-Synopsys, a specialized model that…models · JEV 0.66
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.