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	`cortex run whispervq`

Use it with Jan (UI)

Install Jan using Quickstart
Use in Jan model Hub:
```
cortexso/whispervq 
```

Use it with Cortex (CLI)

Install Cortex using Quickstart
Run the model with command:
```
cortex run whispervq 
```

Credits

Author: HomebrewResearch
Converter: Homebrew
Original License: License
Papers: Paper

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for cortexso/whispervq

Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant

Paper • 2410.15316 • Published Oct 20, 2024 • 12