# Overview

> The languages that UiPath® Document Understanding<sup>TM</sup> models can process are primarily determined by the capabilities of the OCR engine. If the OCR engine is able to recognize a specific language, then the UiPath Document Understanding models **can be trained** to process documents in that language. However, the out-of-the-box **pre-trained models** only support a limited number of languages. If you need to process languages that are not supported out of the box, you will have to further train these models. Additionally, consider the following guidance:

The languages that UiPath® Document Understanding<sup>TM</sup> models can process are primarily determined by the capabilities of the OCR engine. If the OCR engine is able to recognize a specific language, then the UiPath Document Understanding models **can be trained** to process documents in that language. However, the out-of-the-box **pre-trained models** only support a limited number of languages. If you need to process languages that are not supported out of the box, you will have to further train these models. Additionally, consider the following guidance:

* To train a model on Chinese documents, use either the **DocumentUnderstanding** package or the **InvoicesChina** package.
* To train a model on Hebrew documents, use either the **DocumentUnderstanding** package or the **InvoicesHebrew** package.
* To train a model on Japanese documents, use either the **DocumentUnderstanding** package or the **InvoicesJapan** package.
* To train a model on Latin script documents, use any package except for **InvoicesChina**, **InvoicesHebrew**, or **InvoicesJapan**.