---
emoji: "\U0001F4AC"
sdk: static
pinned: false
license: mit
title: Realtime Conversational WebGPU (Vue)
colorFrom: purple
colorTo: indigo
models:
  - HuggingFaceTB/SmolLM2-1.7B-Instruct
  - onnx-community/whisper-base
  - onnx-community/silero-vad
short_description: Yet another Realtime Conversational WebGPU
---

<h1 align="center">Realtime Conversational WebGPU (Vue)</h1>

<p align="center">
  [<a href="https://conversational-webgpu-vue.netlify.app/">Try it</a>]
</p>

> Heavily inspired by [WebGPU Video Object Detection - a Hugging Face Space by WebML Community](https://huggingface.co/spaces/webml-community/webgpu-video-object-detection)

# Realtime Conversational WebGPU

## Getting Started

Follow the steps below to set up and run the application.

### 1. Clone the Repository

Clone the examples repository from GitHub:

```sh
git clone https://github.com/proj-airi/webai-examples.git
```

### 2. Navigate to the Project Directory

Change your working directory to the `conversational-webgpu` folder:

```sh
cd apps/conversational-webgpu
```

### 3. Install Dependencies

Install the necessary dependencies using npm:

```sh
npm i
```

### 4. Run the Development Server

Start the development server:

```sh
npm run dev
```

The application should now be running locally. Open your browser and go to `http://localhost:5175` to see it in action.

## Acknowledgements

Great thanks to what WebML Community have done.

> [Source code](https://huggingface.co/spaces/webml-community/conversational-webgpu)

> [UI inspiration](https://app.sesame.com/)