Trocr Base Str

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

TrOCR is a powerful model for optical character recognition (OCR). It's fine-tuned on the training sets of IC13, IC15, IIIT5K, and SVT. This model 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.

✨ Features

• Encoder - Decoder Architecture: The TrOCR model is an encoder - decoder model. It uses an image Transformer as the encoder and a text Transformer as the decoder. The image encoder is initialized from the weights of BEiT, and the text decoder is initialized from the weights of RoBERTa.
• Patch - based Image Input: Images are presented to the model as a sequence of fixed - size patches (resolution 16x16), which are linearly embedded. Absolute position embeddings are added before feeding the sequence to the Transformer encoder layers. Then, the Transformer text decoder autoregressively generates tokens.

🚀 Quick Start

You can use the raw model for optical character recognition (OCR) on single text - line images. Check the model hub to find fine - tuned versions for tasks that interest 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-base-str')
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-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]

📚 Documentation

Model description

The TrOCR model is an encoder - decoder model, which consists of an image Transformer as the encoder and a text Transformer as the 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.

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}
}