Trocr Large Str

🚀 TrOCR (large-sized model, fine-tuned on STR benchmarks)

The TrOCR model fine-tuned on the training sets of IC13, IC15, IIIT5K, SVT. It's designed for optical character recognition on single text-line images.

🚀 Quick Start

The TrOCR model is an encoder - decoder model, introduced in the paper TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models by Li et al. and first released in this repository. You can use it for optical character recognition (OCR) on single text - line images.

✨ Features

• Encoder - Decoder Architecture: Consists of an image Transformer as encoder and a text Transformer as decoder.
• Pre - trained Initialization: The image encoder is initialized from the weights of BEiT, and the text decoder from the weights of RoBERTa.

📚 Documentation

Model description

The TrOCR model is an encoder - decoder model, with 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.

💻 Usage Examples

Basic Usage

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

# load image from the IIIT - 5k dataset
url = 'https://i.postimg.cc/ZKwLg2Gw/367-14.png'
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")

processor = TrOCRProcessor.from_pretrained('microsoft/trocr-large-str')
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-large-str')
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]

📄 License

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}
}