surya ocr 2

提供商datalab-to
分类ocr
许可证openrail
下载量237
星标1

简介

Surya OCR 2 是一款专注于高精度文档解析的开源 OCR 引擎。与传统 OCR 仅识别文字不同，它在版面分析（Layout Analysis）和多语言识别上表现出色，能精准处理复杂的 PDF、扫描件及多栏排版文档。对于开发者而言，它提供了极佳的本地部署能力，无需依赖昂贵的云端 API 即可实现高效的文档数字化。如果你需要将大量非结构化文档转化为可编辑的 Markdown 或结构化数据，且对识别准确率有较高要求，Surya 是一个极具竞争力的开源替代方案。

核心亮点

  • 强大的版面分析能力，精准识别文档结构
  • 支持多语言识别，适配复杂排版场景
  • 开源可本地部署，无需依赖云端接口
  • 理想的 PDF 转 Markdown 前端处理工具

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("datalab-to/surya-ocr-2")
tokenizer = AutoTokenizer.from_pretrained("datalab-to/surya-ocr-2")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download datalab-to/surya-ocr-2

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download datalab-to/surya-ocr-2 config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('datalab-to/surya-ocr-2')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/datalab-to/surya-ocr-2

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/datalab-to/surya-ocr-2

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('datalab-to/surya-ocr-2')
tokenizer = AutoTokenizer.from_pretrained('datalab-to/surya-ocr-2')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model datalab-to/surya-ocr-2

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model datalab-to/surya-ocr-2 README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('datalab-to/surya-ocr-2')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/datalab-to/surya-ocr-2.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/datalab-to/surya-ocr-2.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook 快速开发

下载并安装 ModelScope library

下载并安装 ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'datalab-to/surya-ocr-2')

完整文档

来源: HuggingFace

---
library_name: transformers
license: openrail
license_link: LICENSE
tags:
- ocr
- pdf
- markdown
- layout
---

<p align="center">
<img src="datalab-logo.png" alt="Datalab Logo" width="150"/>
</p>

<h1 align="center">Datalab</h1>
<p align="center">
<strong>State of the Art models for Document Intelligence</strong>
</p>
<p align="center">
<a href="https://www.datalab.to"><img src="https://img.shields.io/badge/Homepage-datalab.to-blue" alt="Homepage"></a>
<a href="https://documentation.datalab.to"><img src="https://img.shields.io/badge/Docs-Read%20the%20docs-blue" alt="Docs"></a>
<a href="https://www.datalab.to/playground"><img src="https://img.shields.io/badge/Datalab Playground-Try%20it-orange" alt="Datalab Playground"></a>
</p>

<hr/>

Surya

Surya is a 650M param OCR model with these features:

  • Accuracy - scores 83.3% on olmOCR-bench (top under 3B params)
  • Speed - throughput of 5 pages/s on an RTX 5090
  • Multilingual - scores 87.2% on an internal benchmark set of 91 languages (more here)
  • Layout analysis (table, image, header, etc.) with reading order
  • Table recognition (rows + columns)

It works on a range of documents (see usage and benchmarks).

Try Datalab's Managed Platform

Our managed platform runs both Surya, and variants of our highest accuracy model, Chandra.

Get started with $5 in free credits — sign up (takes under 30 seconds) or try our free public playground.

Model Information

<img src="assets/olmocr_size_chart.png" width="700"/>

| Detection | OCR |
|:----------------------------------------------------------------:|:-----------------------------------------------------------------------:|
| <img src="assets/excerpt.png" width="140"/> | <img src="assets/excerpt_text.png" width="140"/> |

| Layout | Table Recognition |
|:------------------------------------------------------------------:|:-------------------------------------------------------------:|
| <img src="assets/excerpt_layout.png" width="140"/> | <img src="assets/scanned_tablerec.png" width="140"/> |

Surya is named for the Hindu sun god, who has universal vision.

Examples

| Name | Detection | OCR | Layout | Order | Table Rec |
|-------------------|:-----------------------------------:|------------------------------------------:|---------------------------------------------:|------------------------------------------------:|------------------------------------------------:|
| Newspaper | Image | Image | Image | Image | |
| Textbook | Image | Image | Image | Image | |
| Tax Form | Image | Image | Image | Image | Image |
| Handwritten Notes | Image | Image | Image | Image | Image |
| Corporate Doc | Image | Image | Image | Image | Image |

Commercial usage

The Surya code is licensed under Apache 2.0. The model weights use a modified AI Pubs Open Rail-M license (free for research, personal use, and startups under $5M funding/revenue). For broader commercial licensing of the model weights, visit our pricing page here.

Installation

Install with:

shell
pip install surya-ocr

Usage

Surya 2 runs layout, OCR, and table recognition through a single VLM served
by vllm (GPU) or llama.cpp (CPU / Apple Silicon). The inference manager
will spawn one for you on first use; you can also point it at an existing
server via SURYA_INFERENCE_URL=http://host:port/v1.

  • Inspect the settings in surya/settings.py. You can override any setting via env var (e.g. SURYA_INFERENCE_BACKEND=vllm).
  • Text detection and OCR errors are separate models.

Interactive App

I've included a streamlit app that lets you interactively try Surya on images or PDF files. Run it with:

shell
pip install streamlit pdftext
surya_gui

OCR (text recognition)

This command will write out a json file with the detected text and bboxes:

shell
surya_ocr DATA_PATH
  • DATA_PATH can be an image, pdf, or folder of images/pdfs
  • --images will save images of the pages and detected blocks (optional)
  • --output_dir specifies the directory to save results to instead of the default
  • --page_range specifies the page range to process in the PDF, specified as a single number, a comma separated list, a range, or comma separated ranges - example: 0,5-10,20.

The results.json file contains a dict keyed by input filename (no extension). Each value is a list of page dicts. Each page dict contains:

  • blocks - per-block OCR results in reading order
- label - canonicalized layout label (e.g. Text, SectionHeader, Table, Equation, Picture, Form, PageHeader, ...). See surya/layout/label.py:LAYOUT_PRED_RELABEL for the full canonical-name set. - raw_label - original label emitted by the model, before canonicalization - reading_order - 0-indexed position in layout output - html - block content as HTML (math wrapped in <math>...</math>, tables as <table>...</table>, etc.). "" if the block was skipped - polygon - 4-corner polygon in [[x0,y0],[x1,y0],[x1,y1],[x0,y1]] order - bbox - axis-aligned [x0, y0, x1, y1] derived from the polygon - confidence - mean per-token probability across the block's decode (0-1) - skipped - true if the block was a visual label (e.g. Picture) and not OCR'd - error - true if the block OCR call failed
  • image_bbox - [0, 0, width, height] for the page image

Performance tips

Throughput is governed by the inference backend, not a RECOGNITION_BATCH_SIZE env var. With vllm, raise --max-num-seqs / --max-num-batched-tokens (or SURYA_INFERENCE_PARALLEL on the client side) to keep more pages in flight. With llama.cpp, set SURYA_INFERENCE_PARALLEL to match --parallel on llama-server.

From python

python
from PIL import Image
from surya.inference import SuryaInferenceManager
from surya.recognition import RecognitionPredictor

manager = SuryaInferenceManager()
recognition_predictor = RecognitionPredictor(manager)


Default: full-page OCR. One VLM call per page; returns layout + content as


HTML <div data-bbox=... data-label=...> blocks.

predictions = recognition_predictor([Image.open(IMAGE_PATH)])

Block mode: pre-run layout, then per-block OCR. Auto-selected when


layout_results is passed.

from surya.layout import LayoutPredictor
layout = LayoutPredictor(manager)
layouts = layout([Image.open(IMAGE_PATH)])
predictions = recognition_predictor([Image.open(IMAGE_PATH)], layouts)

##

查看官方来源