---
license: apache-2.0
---
## Overview

**WhisperVQ** 

WhisperVQ is a quantizer model and a key component of WhisperSpeech. It compresses speech into discrete tokens, enabling seamless compatibility with large language models (LLMs) for real-time speech understanding and various downstream tasks.

## Variants

| No | Variant | Cortex CLI command |
| --- | --- | --- |
| 1 | [gguf](https://huggingface.co/cortexso/whispervq/tree/main) | `cortex run whispervq` |


## Use it with Jan (UI)

1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
2. Use in Jan model Hub:
    ```text
    cortexso/whispervq 
    ```
## Use it with Cortex (CLI)

1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
2. Run the model with command:
    ```bash
    cortex run whispervq 
    ```
## Credits

- **Author:** HomebrewResearch
- **Converter:** [Homebrew](https://www.homebrew.ltd/)
- **Original License:** [License]()
- **Papers:** [Paper](https://arxiv.org/abs/2410.15316)