Skip to content
@Remtir

Remtir

Thai AI research lab for computer vision. We build open models for reading Thai documents: OCR, layout and tables.

Remtir

Remtir is a Thai AI research lab working on computer vision. We focus on what Thai documents and images need, which global models often get wrong: stacked vowels and tone marks, Thai digits, government forms, dense tables and pages photographed on a phone.

ห้องวิจัย AI ไทยด้าน Computer Vision พัฒนาโมเดลอ่านเอกสารและภาพภาษาไทยแบบเปิด

What we work on

  • Document AI: OCR, layout analysis, reading order and table structure for Thai and English documents
  • Text recognition: recognizers built around Thai script, such as grapheme-cluster CTC
  • Efficient vision models: small models that run on CPU and on-premise, so documents never have to leave the building
  • Evaluation: fair, reproducible benchmarks for Thai OCR

Projects

Project What it is
AksonOCR-Lite Open-source Thai document OCR on ONNX Runtime: PDF/image → Markdown, layout and tables, ~1.5 s/page on CPU. Apache-2.0. Live demo · Weights
AksonOCR Our document parsing API for harder pages: handwriting, charts, formulas and key extraction.

Links

Website · Hugging Face · Blog

Popular repositories Loading

  1. AksonOCR-Lite AksonOCR-Lite Public

    Thai document OCR with a grapheme-cluster CTC recognizer. 81M params, runs on CPU: ~3x faster per page than 2B-param OCR VLMs on a GPU, and more accurate than VLMs on average.

    Python 56 8

  2. .github .github Public

    Remtir organization profile

Repositories

Showing 2 of 2 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…