---
title: "OcrModel"
sidebar_label: "OcrModel"
description: "The clika_runtime.modelverse.models OcrModel class."
---

<!-- Generated by tools/api_reference/generate_api_docs.py. Do not edit. -->

A loaded OCR model.

## `recognize`

```python
recognize(self, image: 'clika_runtime.Tensor', *, max_new_tokens: 'int' = 0) -> 'str'
```

The text in an [H, W, 3] image.

## `recognize_pages`

```python
recognize_pages(self, pages: 'Sequence[clika_runtime.Tensor]', *, max_new_tokens: 'int' = 0) -> 'str'
```

The text of one document, its [H, W, 3] pages in order. A model that
reads one image per request refuses more than one page.