trocr small handwritten

提供商microsoft
分类image-to-text
许可证Apache-2.0
下载量193
星标0

简介

TrOCR-small-handwritten 是微软推出的轻量级光学字符识别（OCR）模型，专门针对手写文本识别进行了优化。它摒弃了传统的 OCR 管道，采用 Transformer 架构直接将图像转化为文本，能有效处理书写风格多样、笔迹不规整的场景。由于参数量较小，该模型在保证识别精度的同时，具备极高的推理速度，非常适合部署在资源受限的边缘设备或需要实时响应的端侧应用中。对于开发者来说，它是一个低门槛的替代方案，可快速集成到笔记数字化或表单自动识别等工作流中。

核心亮点

  • 专注手写体识别，对非标准笔迹兼容性强
  • 轻量化架构，推理速度快且资源占用低
  • 端到端 Transformer 结构，无需复杂预处理
  • Apache-2.0 协议，支持商业化自由部署

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("microsoft/trocr-small-handwritten")
tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-small-handwritten")

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 microsoft/trocr-small-handwritten

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 microsoft/trocr-small-handwritten 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('microsoft/trocr-small-handwritten')

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/microsoft/trocr-small-handwritten

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/microsoft/trocr-small-handwritten

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('microsoft/trocr-small-handwritten')
tokenizer = AutoTokenizer.from_pretrained('microsoft/trocr-small-handwritten')

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 microsoft/trocr-small-handwritten

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 microsoft/trocr-small-handwritten 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('microsoft/trocr-small-handwritten')

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/microsoft/trocr-small-handwritten.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/microsoft/trocr-small-handwritten.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', 'microsoft/trocr-small-handwritten')

完整文档

来源: HuggingFace

---
tags:

  • trocr

  • image-to-text

widget:
  • src: https://fki.tic.heia-fr.ch/static/img/a01-122-02.jpg

example_title: Note 1
  • src: https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSoolxi9yWGAT5SLZShv8vVd0bz47UWRzQC19fDTeE8GmGv_Rn-PCF1pP1rrUx8kOjA4gg&usqp=CAU

example_title: Note 2
  • src: https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRNYtTuSBpZPV_nkBYPMFwVVD9asZOPgHww4epu9EqWgDmXW--sE2o8og40ZfDGo87j5w&usqp=CAU

example_title: Note 3
---

TrOCR (small-sized model, fine-tuned on IAM)

TrOCR model fine-tuned on the IAM dataset. It was introduced in the paper TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models by Li et al. and first released in this repository.

Model description

The TrOCR model is an encoder-decoder model, consisting of an image Transformer as encoder, and a text Transformer as decoder. The image encoder was initialized from the weights of DeiT, while the text decoder was initialized from the weights of UniLM.

Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder. Next, the Transformer text decoder autoregressively generates tokens.

Intended uses & limitations

You can use the raw model for optical character recognition (OCR) on single text-line images. See the model hub to look for fine-tuned versions on a task that interests you.

How to use

Here is how to use this model in PyTorch:

python
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
import requests

load image from the IAM database

url = 'https://fki.tic.heia-fr.ch/static/img/a01-122-02-00.jpg'
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")

processor = TrOCRProcessor.from_pretrained('microsoft/trocr-small-handwritten')
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-small-handwritten')
pixel_values = processor(images=image, return_tensors="pt").pixel_values


generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

BibTeX entry and citation info

bibtex
@misc{li2021trocr,
      title={TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models}, 
      author={Minghao Li and Tengchao Lv and Lei Cui and Yijuan Lu and Dinei Florencio and Cha Zhang and Zhoujun Li and Furu Wei},
      year={2021},
      eprint={2109.10282},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
查看官方来源