模型:
naver-clova-ix/donut-base-finetuned-zhtrainticket
Donut模型在ZhTrainTicket上进行了微调。它首次在Geewok等人的论文 OCR-free Document Understanding Transformer 中提出,并于 this repository 首次发布。
免责声明:发布Donut模型的团队未为该模型编写模型卡,因此此模型卡由Hugging Face团队编写。
Donut包括一个视觉编码器(Swin Transformer)和一个文本解码器(BART)。给定一个图像,编码器首先将图像编码为嵌入向量张量(形状为batch_size、seq_len、hidden_size),然后解码器在编码器的编码的条件下自回归生成文本。
此模型在ZhTrainTicket上进行了微调,该数据集用于文档解析。
我们参考 documentation 中的代码示例。
@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} }