Export
TeleOCR
/wiki/teleocr
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in Claude
Sending this to someone?
MarkdownPlain text for notes apps and AI chats
WordA document to edit and annotate
PDFA4, for printing and sharing
ZIPEverything: the documents, the data, and instructions for AI assistants
Share the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
stub ·
1 feed
TeleOCR
1.2B-parameter open-source vision-language model for structured document parsing from camera and digital sources
Snapshot
Intelligence coverage
TeleOCR is a 1.2B-parameter open-source vision-language-model designed for structured document parsing from both camera and digital image sources 1.
The model is built on the transformers platform 2 and is developed by XingChen-AGI 2.
Facts 2
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Vendor | XingChen-AGI | low | 1 | 2 |
| Category | vision-language-model | low | 1 | 2 |
Platform 1
Transformers
Involved in 1
Official links
No official links recorded yet.
Work here? Claim this page with a verified company email or DNS record.
Frequently mentioned together 9
Sources 4
- The TechBeat: GPT 6 Astra - Will It Shake Up the World of Marketing? (10/29/2026) · HackerNoon
- TeleOCR: A 1.2B Vision-Language Model for Structured Document Parsing · HackerNoon
- Xiaomi-OCR-0: A 0.8B AI Model for Document Parsing and OCR · HackerNoon
- The TechBeat: Why Knowledge Graphs and Ontologies Are Making a Comeback in the Age of AI (11/2/2026) · HackerNoon