|
--- |
|
license: mit |
|
language: |
|
- en |
|
--- |
|
|
|
# Visually Guided Generative Text-Layout Pre-training for Document Intelligence |
|
|
|
The ViTLP model was proposed in [Visually Guided Generative Text-Layout Pre-training for Document Intelligence](https://arxiv.org/abs/2403.16516), which is a generative foundation model for document intelligence. We provide the pre-trained checkpoint *ViTLP-medium* (380M). The pre-trained ViTLP model can natively perform OCR text localization and recognition. |
|
|
|
|
|
## Demo on Document Text Recognition & Localization |
|
|
|
The code of ViTLP inference and demo is assisible at [https://github.com/Veason-silverbullet/ViTLP](https://github.com/Veason-silverbullet/ViTLP). |
|
|
|
 |
|
|
|
 |
|
|
|
|
|
# Preset FAQ |
|
- Why is ViTLP-medium (380M)? |
|
|
|
When I commenced this project, it was on the eve of LLMs (precisely speaking, ChatGPT). ViTLP-base presented in our paper, is actually a rather small pre-trained model. We know it is expected to scale up ViTLP in this LLM era. However, the pre-training scale is commonly constrained by computation resources and the pre-training dataset scale, in which context ViTLP-medium (380M) is the largest pre-training scale so far we can support. |
|
|
|
Besides, this scale of ViTLP also brings inference sweetness including speed and memory usage. Typically, OCR on a page of a document image can be processed within 5~10 seconds in an Nvidia 4090, which is comparable to (and faster than) most OCR engines (and LLMs). |
|
|
|
|
|
# Note |
|
ViTLP is pronounced /ˈvai·tlp/ (vital). The first version of our paper was submitted to [OpenReview](https://openreview.net/forum?id=ARtBIBAmNR) in June 2023. |
