donut-base-finetuned-docvqa is a fine-tuned version of the Donut model specialized for document visual question answering. It understands document images and answers questions directly from visual content. The model is available on Hugging Face with Transformers integration for developers building document intelligence applications.
Donut Base Finetuned Docvqa sits in PulseGate's Foundation models & chat category. It focuses on answering questions about document images without manual OCR or data extraction. It is built as an open-source project for developers. The project is open source (MIT). Donut Base Finetuned Docvqa is available on the web and API.
It is developed by NAVER Clova, and it first shipped in 2022. The project is developed in the open on GitHub with 6.9k stars. Key capabilities include Document QA, Visual Question Answering, and Transformers Compatible.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do