Cherryblade29/ocr

Usage

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10：

torch==2.0.1
torchvision==0.15.2
transformers==4.37.2
tiktoken==0.6.0
verovio==4.3.1
accelerate==0.28.0

from transformers import AutoModel, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('Cherryblade29/ocr', trust_remote_code=True)
model = AutoModel.from_pretrained('Cherryblade29/ocr', trust_remote_code=True, low_cpu_mem_usage=True, device_map='cuda', use_safetensors=True, pad_token_id=tokenizer.eos_token_id)
model = model.eval().cuda()


# input your test image
image_file = 'xxx.jpg'

# plain texts OCR
res = model.chat(tokenizer, image_file, ocr_type='ocr')

# format texts OCR:
# res = model.chat(tokenizer, image_file, ocr_type='format')

# fine-grained OCR:
# res = model.chat(tokenizer, image_file, ocr_type='ocr', ocr_box='')
# res = model.chat(tokenizer, image_file, ocr_type='format', ocr_box='')
# res = model.chat(tokenizer, image_file, ocr_type='ocr', ocr_color='')
# res = model.chat(tokenizer, image_file, ocr_type='format', ocr_color='')

# multi-crop OCR:
# res = model.chat_crop(tokenizer, image_file, ocr_type='ocr')
# res = model.chat_crop(tokenizer, image_file, ocr_type='format')

# render the formatted OCR results:
# res = model.chat(tokenizer, image_file, ocr_type='format', render=True, save_render_file = './demo.html')

print(res)