KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#developer-tools #typescript #codex #ai-agents #claude-code #dsh #dsh-plugin #cli #macos #ai-agent #deepseek-harness #open-source

sparrow-donut

★ 57 Open GitHub ↗

Data extraction with Donut ML model

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Sparrow Donut
Data extraction with ML

## The Principle

Sparrow is an innovative open-source solution designed for efficient data extraction and processing from various documents and images. It seamlessly handles forms, invoices, receipts, and other unstructured data sources. Sparrow stands out with its modular architecture, offering independent services such as OCR, Donut fine-tuning/inference, and a data labeling UI, all optimized for robust performance.

### Services

* **[sparrow-data](https://github.com/katanaml/sparrow-donut/tree/main/sparrow-data/)** - This service focuses on data preparation specifically for the Donut ML model, including fine-tuning and OCR integration.
* **[sparrow-ml](https://github.com/katanaml/sparrow-donut/tree/main/sparrow-ml/)** - Dedicated to the Donut ML model, this service handles both fine-tuning and inference, streamlining the machine learning workflow.
* **[sparrow-ui](https://github.com/katanaml/sparrow-donut/tree/main/sparrow-ui/)** - A user-friendly interface for managing Donut ML model data labeling services and a dashboard.

## Installation

### Donut

Follow the install steps outlined here:

1. Donut Data <a href="https://github.com/katanaml/sparrow-donut/tree/main/sparrow-data/">install steps</a>

2. Donut ML <a href="https://github.com/katanaml/sparrow-donut/tree/main/sparrow-ml/">install steps</a>

3. Donut UI <a href="https://github.com/katanaml/sparrow-donut/tree/main/sparrow-ui/">install steps</a>

## Usage

### Donut

Follow the steps outlined here:

1. Donut Data <a href="https://github.com/katanaml/sparrow-donut/tree/main/sparrow-data/">usage steps</a>

2. Donut ML <a href="https://github.com/katanaml/sparrow-donut/tree/main/sparrow-ml/">usage steps</a>

3. Donut UI <a href="https://github.com/katanaml/sparrow-donut/tree/main/sparrow-ui/">usage steps</a>

## Examples

### Inference with Donut ML model

Sparrow UI:

![Inference Results](https://github.com/katanaml/sparrow-donut/blob/main/sparrow-ui/assets/inference_actual.png)

## Author

[Katana ML](https://katanaml.io), [Andrej Baranovskij](https://github.com/abaranovskis-redsamurai)

## License

sparrow-donut

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README