inference-providers/pr_2713/en/tasks/summarization.md

## Summarization

Summarization is the task of producing a shorter version of a document while preserving its important information. Some models can extract text from the original input, while other models can generate entirely new text.

> [!TIP]
> For more details about the `summarization` task, check out its [dedicated page](https://huggingface.co/tasks/summarization)! You will find examples and related materials.

### Recommended models

- [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn): A strong summarization model trained on English news articles. Excels at generating factual summaries.
- [Falconsai/medical_summarization](https://huggingface.co/Falconsai/medical_summarization): A summarization model trained on medical articles.

Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=summarization&sort=trending), or from the terminal with the [`hf` CLI](https://huggingface.co/docs/huggingface_hub/package_reference/cli#hf-models-list):

```bash
hf models ls --warm --pipeline-tag summarization --sort trending_score
```

### Using the API

<InferenceSnippet
    pipeline=summarization
    providersMapping={ {"hf-inference":{"modelId":"human-centered-summarization/financial-summarization-pegasus","providerModelId":"human-centered-summarization/financial-summarization-pegasus"}} }
/>

### API specification

#### Request

| Headers |   |    |
| :--- | :--- | :--- |
| **authorization** | _string_ | Authentication header in the form `'Bearer: hf_****'` when `hf_****` is a personal user access token with "Inference Providers" permission. You can generate one from [your settings page](https://huggingface.co/settings/tokens/new?ownUserPermissions=inference.serverless.write&tokenType=fineGrained). |

| Payload |  |  |
| :--- | :--- | :--- |
| **inputs*** | _string_ | The input text to summarize. |
| **parameters** | _object_ |  |
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;clean_up_tokenization_spaces** | _boolean_ | Whether to clean up the potential extra spaces in the text output. |
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;truncation** | _enum_ | Possible values: do_not_truncate, longest_first, only_first, only_second. |
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generate_parameters** | _object_ | Additional parametrization of the text generation algorithm. |

#### Response

| Body |  |
| :--- | :--- | :--- |
| **summary_text** | _string_ | The summarized text. |