Metadata-Version: 2.1
Name: whisper-mps
Version: 0.0.3
Summary: with Apple MPS support for OpenAI Whisper
Author-Email: wushuhong <wushuhong@atomgradient.com>
License: MIT
Requires-Python: >=3.11
Requires-Dist: moviepy==1.0.3
Requires-Dist: pytube==15.0.0
Requires-Dist: mlx>=0.0.5
Requires-Dist: numba>=0.58.1
Requires-Dist: numpy>=1.26.2
Requires-Dist: torch>=2.1.1
Requires-Dist: tqdm>=4.66.1
Requires-Dist: more-itertools>=10.1.0
Requires-Dist: tiktoken==0.3.3
Requires-Dist: rich>=13.7.0
Description-Content-Type: text/markdown

# whisper-mps

An opinionated CLI to transcribe Audio files w/ Whisper on-device! Powered by  *MLX*, *Whisper* & *Apple M series*

**TL;DR** - After our actual testing. The Whisper supported by MPS achieves speeds comparable to 4090!


## 🆕 Blazingly fast transcriptions via your terminal! ⚡️

We've added a CLI to enable fast transcriptions. Here's how you can use it:

Install `whisper-mps` with `pip`:

```bash
pip install whisper-mps
```

Run inference from any path on your computer:

```bash
whisper-mps --file-name < wav filename >
```


> [!NOTE]
> The CLI is highly opinionated and only works on Apple MPS.

## CLI Options

The `whisper-mps` repo provides an all round support for running Whisper in various settings. More command-line support will be provided later

```
  --file-name FILE_NAME
                        Path or URL to the audio file to be transcribed.
```
