Downloads · 30 days
46
3% of all-time downloads
ZihCiLin/trocr-traditional-chinese-historical-finetune
trocr-traditional-chinese-historical-finetune is a image-to-text model from ZihCiLin. Use it when you need a caption or text from an image. It is set up for transformers.
This is a TrOCR model finetuned on Lo Chia-Luen historical manuscripts for Traditional Chinese historical document recognition.
Downloads · 30 days
46
3% of all-time downloads
All-time downloads
1.4K
Public
Parameters
309M
1.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.2 GB · 100%
From the Hugging Face model README
This is a TrOCR model finetuned on Lo Chia-Luen historical manuscripts for Traditional Chinese historical document recognition.
This finetuned model is optimized for:
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
# Load model and processor
processor = TrOCRProcessor.from_pretrained("ZihCiLin/trocr-traditional-chinese-historical-finetune")
model = VisionEncoderDecoderModel.from_pretrained("ZihCiLin/trocr-traditional-chinese-historical-finetune")
# Load historical document image
image = Image.open("historical_manuscript.jpg").convert("RGB")
# Generate text
pixel_values = processor(image, return_tensors="pt").pixel_values
generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(generated_text)
For best results, use with LLM-guided decoding:
# See: https://github.com/Jason9339/traditional-chinese-historical-document-ocr-llm-fusion
# Fusion with Breeze-7B improves CER by 10% on historical documents
If you use this model, please cite:
@inproceedings{lin2026decoding,
title={Decoding-Time Fusion of OCR and Large Language Models for Traditional Chinese Historical Document Recognition},
author={Lin, Zih-Ci and Liao, Wen-Hung},
booktitle={International Conference on Pattern Recognition (ICPR)},
year={2026}
}
This work is based on the Lo Chia-Luen Manuscripts from the Special Collection Center of NCCU Libraries.