StarDoc-AI/TeleOCR
image-text-to-text model by StarDoc-AI
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Earlier source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents [](LICENSE) [](https://github.com/caipeng328/TeleOCR) [](https://paperswithcode.co/api/v1/papers/2608.12898/leaderboard-badge-link?eval=25856) [](https://www.teleai.com.cn/docparse/DocumentParsing) [](https://arxiv.org/abs/2608.12898) TeleOCR is a lightweight (1.2B parameters), open-source Vision-Language Model designed specifically for document parsing. Unlike existing methods that mainly target either digital documents or camera-captured documents, TeleOCR unifies both scenarios within a single framework. Compared with previous document parsing models, TeleOCR introduces These techniques enable TeleOCR to achieve state-of-the-art performance on both digital and camera-captured document benchmarks while remaining lightweight enough for practical deployment. TeleOCR achieves state-of-the-art performance on multiple public document parsing benchmarks. To evaluate the model's ability to understand complex document deformations, we conduct a visual evaluation on the public dewarping datasets DocUNet and DIR300, with representative results shown in Figure.…
The latest refresh did not succeed. This is the last available preview; check the original for changes.
Read the full model card ↗ · Preview checked 2026-09-26T18:38:50.132Z
Inside the original model card — Document outline
- 🔥 News
- 📖 Introduction
- 📊 Experimental Results
- Layout Visualization of Distorted Documents
- Dr.DocBench Challenge
- OmniDocBench v1.6
- WildOmniDocBench
- PureDocBench
- ICDAR2026 Sci-ImageMiner
- 🚀 Installation
- Quick Start
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
StarDoc-AI/TeleOCR is a image-text-to-text model repository published by StarDoc-AI on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 26,152
- Cumulative likes
- 444
- Hugging Face trending score
- 376
- Reported safetensors parameters
- 1,415,072,768
- Architecture
- Qwen2_5_VLForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-08-14T06:15:03.000Z
- Last modified
- 2026-09-22T06:48:34.000Z
Compatibility and lineage
Reported languages: zh, en
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-27T06:37:50.689Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.