ModelPublicadoExterno

Trocr Small Printed

TrOCR model fine-tuned on the SROIE 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.

Fuentehuggingface.co/IBRAHIM1990/trocr-small-printed/tree/04a028202e9f02e46bc1146c2da56508a4ec431b

TipoText modelVersiónUnratedcalidad

Fuente del modelo

Tipo: Text model
Tamaño del archivo: 234–235 MB
Versión: vRevision 04a0282
Actualizado: 5 nov 2026
Descargas: 2
Fuente: Hugging Face

Descripción de la fuente

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

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:

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

# load image from the IAM database (actually this model is meant to be used on printed text)
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-printed')
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-small-printed')
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

@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}
}

Requisitos

Modelos

pytorch_model.bin
Repositorio identificado
Clip Vision · Hugging Face · IBRAHIM1990/trocr-small-printed

Fuentes

1 fuente

Hugging FacePrincipalVersión 04a028202e9f02e46bc1146c2da56508a4ec431b

huggingface.co/IBRAHIM1990/trocr-small-printed/tree/04a028202e9f02e46bc1146c2da56508a4ec431b

Verificado 5 nov

Download files

Repository files

File inventory only; completeness is unverified.

Artefactos del modelo

2 artefactos

model.safetensors

safetensors · FP32 (tensor header) · 234 MB · SHA-256 49350a39968d…03f3 · Hugging Face

Download file

pytorch_model.bin

bin · 235 MB · SHA-256 159af16f37ca…0635 · Hugging Face

Download file

Extractos de fuentes

3 extractos

Readme27 agohuggingface.co/IBRAHIM1990/trocr-small-printed

--- tags: - trocr - image-to-text widget: - src: https://layoutlm.blob.core.windows.net/trocr/dataset/SROIE2019Task2Crop/train/X00016469612_1.jpg example_title: Printed 1 - src: https://layoutlm.blob.core.windows.net/trocr/dataset/SROIE2019Task2Crop/train/X51005255805_7.jpg example_title: Printed 2 - src: https://layoutlm.blob.core.windows.net/trocr/dataset/SROIE2019Task2Crop/train/X51005745214_6.jpg example_title: Printed 3 --- # TrOCR (small-sized model, fine-tuned on SROIE) TrOCR model fine-tuned on the [SROIE dataset](https://rrc.cvc.uab.es/?ch=13). It was introduced in the paper [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282) by Li et al. and first released in [this repository](https://github.com/microsoft/unilm/tree/master/trocr). ## 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](https://huggingface.co/models?search=microsoft/trocr) 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 (actually this model is meant to be used on printed text) 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-printed') model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-small-printed') pixel_values = processor(images=image, return_tensors="pt").pixel_values generated_ids = model.generate(pixel_values) generated_text = processor.batch_decode(generated_ids,...

Note5 novhuggingface.co/IBRAHIM1990/trocr-small-printed

Source context: 2 downloads · 0 likes · Pipeline image-to-text · Repo IBRAHIM1990/trocr-small-printed

Note27 agohuggingface.co/IBRAHIM1990/trocr-small-printed

Source context: 5 downloads · 0 likes · Pipeline image-to-text · Repo IBRAHIM1990/trocr-small-printed