|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
datasets: |
|
|
- YuukiAsuna/VietnameseTableVQA |
|
|
language: |
|
|
- vi |
|
|
base_model: |
|
|
- naver-clova-ix/donut-base |
|
|
pipeline_tag: document-question-answering |
|
|
--- |
|
|
|
|
|
# Model Card for Model ID |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
|
|
VieTable Donut DocVQA is a fine-tuned version of the Donut model for the Vietnamese DocVQA (Table data) |
|
|
|
|
|
|
|
|
### BibTeX entry and citation info |
|
|
|
|
|
```bibtex |
|
|
@article{DBLP:journals/corr/abs-2111-15664, |
|
|
author = {Geewook Kim and |
|
|
Teakgyu Hong and |
|
|
Moonbin Yim and |
|
|
Jinyoung Park and |
|
|
Jinyeong Yim and |
|
|
Wonseok Hwang and |
|
|
Sangdoo Yun and |
|
|
Dongyoon Han and |
|
|
Seunghyun Park}, |
|
|
title = {Donut: Document Understanding Transformer without {OCR}}, |
|
|
journal = {CoRR}, |
|
|
volume = {abs/2111.15664}, |
|
|
year = {2021}, |
|
|
url = {https://arxiv.org/abs/2111.15664}, |
|
|
eprinttype = {arXiv}, |
|
|
eprint = {2111.15664}, |
|
|
timestamp = {Thu, 02 Dec 2021 10:50:44 +0100}, |
|
|
biburl = {https://dblp.org/rec/journals/corr/abs-2111-15664.bib}, |
|
|
bibsource = {dblp computer science bibliography, https://dblp.org} |
|
|
} |
|
|
``` |
