https://github.com/gh640/mlx-whisper-webui

Fast STT (Speach-to-Text) Web UI with mlx-whisper
https://github.com/gh640/mlx-whisper-webui

gradio mlx mlx-whisper speech-to-text stt

Last synced: about 1 month ago
JSON representation

Fast STT (Speach-to-Text) Web UI with mlx-whisper

• Host: GitHub
• URL: https://github.com/gh640/mlx-whisper-webui
• Owner: gh640
• Created: 2024-10-16T07:33:01.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2024-10-16T07:42:07.000Z (2 months ago)
• Last Synced: 2024-10-19T02:16:31.780Z (2 months ago)
• Topics: gradio, mlx, mlx-whisper, speech-to-text, stt
• Language: Python
• Homepage:
• Size: 69.3 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# `mlx-whisper` Web UI

Fast STT (Speach-to-Text) Web UI with mlx-whisper. The model is Whisper Large-3-Turbo.

## Prerequisites

- Apple Silicon Mac

- Python `>=3.12`

- uv `>=0.4.0`

## Usage

Install the packages.

```bash

uv sync

```

Run the app.

```bash

uv run main.py

```

Open http://127.0.0.1:7860 with your browser and you can view the app.

![screenshot](./assets/screenshot-1.png)

## Reference

- [mlx-whisper · PyPI](https://pypi.org/project/mlx-whisper/)

- [gradio · PyPI](https://pypi.org/project/gradio/)

- [openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision](https://github.com/openai/whisper)