davanstrien/falcon-ocr-layout-test

---
tags:
- ocr
- document-processing
- falcon-ocr
- layout
- uv-script
- generated
---

# Document Processing using Falcon OCR (layout mode)

This dataset contains OCR results from images in [davanstrien/ufo-ColPali](https://huggingface.co/datasets/davanstrien/ufo-ColPali) using [Falcon OCR](https://huggingface.co/tiiuae/Falcon-OCR), a 0.3B early-fusion vision-language model.

## Processing Details

- **Source Dataset**: [davanstrien/ufo-ColPali](https://huggingface.co/datasets/davanstrien/ufo-ColPali)
- **Model**: [tiiuae/Falcon-OCR](https://huggingface.co/tiiuae/Falcon-OCR)
- **Task Mode**: `layout` - Layout-aware OCR (region detection + per-region extraction)
- **Number of Samples**: 5
- **Processing Time**: 0.9 min
- **Processing Date**: 2026-04-08 05:50 UTC
- **Backend**: falcon-perception (OCRInferenceEngine)

## Reproduction

```bash
uv run https://huggingface.co/datasets/uv-scripts/ocr/raw/main/falcon-ocr.py \
davanstrien/ufo-ColPali \
<output-dataset> \
--task-mode layout \
--image-column image
```

Generated with [UV Scripts](https://huggingface.co/uv-scripts)

tags:
- 光学字符识别（OCR，Optical Character Recognition）
- 文档处理
- Falcon OCR
- 版面布局
- UV脚本
- 生成式

# 基于Falcon OCR（版面布局模式）的文档处理

本数据集包含使用[Falcon OCR](https://huggingface.co/tiiuae/Falcon-OCR)——一款0.3B参数的早期融合型视觉语言模型——对[davanstrien/ufo-ColPali](https://huggingface.co/datasets/davanstrien/ufo-ColPali)数据集中的图像进行处理所得的光学字符识别结果。

## 处理详情

- **源数据集**: [davanstrien/ufo-ColPali](https://huggingface.co/datasets/davanstrien/ufo-ColPali)
- **所用模型**: [tiiuae/Falcon-OCR](https://huggingface.co/tiiuae/Falcon-OCR)
- **任务模式**: `layout` —— 支持版面感知的光学字符识别（即区域检测与逐区域内容提取）
- **样本数量**: 5
- **处理耗时**: 0.9分钟
- **处理日期**: 2026-04-08 05:50 UTC
- **处理后端**: falcon-perception（OCRInferenceEngine）

## 复现方法

bash
uv run https://huggingface.co/datasets/uv-scripts/ocr/raw/main/falcon-ocr.py
davanstrien/ufo-ColPali
<output-dataset>
--task-mode layout
--image-column image

本数据集由[UV Scripts](https://huggingface.co/uv-scripts)生成。