bytefer/ollama-ocr
Implementing OCR with a local visual model run by ollama.
This tool helps you accurately extract text from images while preserving its original layout and formatting. You provide a JPG, JPEG, or PNG image, and it outputs the recognized text, optionally in Markdown. It's designed for developers or technical users who need to automate text extraction from documents, photos, or scanned materials.
300 stars. No commits in the last 6 months. Available on npm.
Use this if you need a reliable way to get structured text from images using locally-run, powerful visual AI models and you have the technical skills to integrate a Node.js library.
Not ideal if you're looking for a simple, plug-and-play OCR application without any programming or if you need to process file formats other than JPG, JPEG, or PNG.
Stars
300
Forks
28
Language
TypeScript
License
MIT
Category
Last pushed
Nov 27, 2024
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/bytefer/ollama-ocr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
clusterzx/paperless-ai
An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure...
kha-white/manga-ocr
Optical character recognition for Japanese text, with the main focus being Japanese manga
alephpi/Texo-web
The web application for Texo, a minimalist SOTA LaTeX OCR model which contains only 20M...
alephpi/Texo
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training...
Dartvauder/NeuroSandboxWebUI
(Windows/Linux/MacOS) Local WebUI with neural network models (Text, Image, Video, 3D, Audio) on...