README.md

metadata

language:
  - ko
tags:
  - ocr
widget:
  - src: https://raw.githubusercontent.com/ddobokki/ocr_img_example/master/g.jpg
    example_title: word1
  - src: https://raw.githubusercontent.com/ddobokki/ocr_img_example/master/khs.jpg
    example_title: word2
  - src: https://raw.githubusercontent.com/ddobokki/ocr_img_example/master/m.jpg
    example_title: word3

korean trocr model

train datasets

AI Hub

• 다양한 형태의 한글 문자 OCR
• 공공행정문서 OCR

model structure

• encoder : trocr-base-stage1's encoder
• decoder : KR-BERT-char16424

how to use

from transformers import TrOCRProcessor, VisionEncoderDecoderModel, AutoTokenizer
import requests 
import unicodedata
from io import BytesIO
from PIL import Image

processor = TrOCRProcessor.from_pretrained("ddobokki/ko-trocr") 
model = VisionEncoderDecoderModel.from_pretrained("ddobokki/ko-trocr")
tokenizer = AutoTokenizer.from_pretrained("ddobokki/ko-trocr")

url = "https://raw.githubusercontent.com/ddobokki/ocr_img_example/master/g.jpg"
response = requests.get(url)
img = Image.open(BytesIO(response.content))

pixel_values = processor(img, return_tensors="pt").pixel_values 
generated_ids = model.generate(pixel_values, max_length=64)
generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
generated_text = unicodedata.normalize("NFC", generated_text)
print(generated_text)