Trocr Base Stage1

🚀 TrOCR (base-sized model, pre-trained only)

TrOCR is a pre-trained only model. It addresses the challenge of optical character recognition (OCR) by leveraging pre - trained Transformer models, offering a powerful solution for converting text in images to machine - readable text.

🚀 Quick Start

TrOCR is an encoder - decoder model. The encoder is an image Transformer, and the decoder is a text Transformer. The image encoder is initialized with BEiT weights, and the text decoder with RoBERTa weights. You can use the raw model for OCR on single text - line images.

✨ Features

• Encoder - Decoder Architecture: Combines an image Transformer encoder and a text Transformer decoder for effective OCR.
• Pre - trained Weights: Initializes the image encoder from BEiT and the text decoder from RoBERTa, leveraging pre - trained knowledge.

📚 Documentation

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:

Basic Usage

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-stage1')
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-stage1')

# training
pixel_values = processor(image, return_tensors="pt").pixel_values  # Batch size 1
decoder_input_ids = torch.tensor([[model.config.decoder.decoder_start_token_id]])
outputs = model(pixel_values=pixel_values, decoder_input_ids=decoder_input_ids)

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}
}

⚠️ Important Note

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.