trocr base handwritten

提供商microsoft
分类image-to-text
许可证mit
下载量276
星标1

简介

TrOCR base handwritten 是微软推出的端到端光学字符识别（OCR）模型，专门针对手写文本识别进行了优化。与传统 OCR 先分割字符再识别的方案不同，它采用了 Transformer 架构，直接将图像序列映射为文本，极大地提升了对潦草手写体和不规则排版的识别精度。对于开发者而言，该模型上手门槛较低，可通过 Hugging Face 等平台快速部署，非常适合用于数字化手写笔记、表单自动录入等需要高鲁棒性文本提取的场景，是构建垂直领域 OCR 应用的理想基础模型。

核心亮点

  • 端到端 Transformer 架构，无需复杂预处理
  • 专注手写体识别，对不规则笔迹兼容性强
  • MIT 协议开源，商业化部署灵活无压力
  • 适配 Hugging Face 生态，快速实现推理部署

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-base-handwritten")
tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-base-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-base-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-base-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-base-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-base-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-base-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-base-handwritten')
tokenizer = AutoTokenizer.from_pretrained('microsoft/trocr-base-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-base-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-base-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-base-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-base-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-base-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-base-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
license: mit
---

TrOCR (base-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.

Disclaimer: The team releasing TrOCR did not write a model card for this model so this model card has been written by the Hugging Face team.

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 BEiT, while the text decoder was initialized from the weights of RoBERTa.

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-base-handwritten')
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-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