[Whisper] Load customized MLX model & Quantization (#191)

* Add option to load customized mlx model

* Add quantization

* Apply reviews

* Separate model conversion and loading

* Update test

* Fix benchmark

* Add notes about conversion

* Improve doc

whisper/README.md

@@ -6,7 +6,7 @@ parameters[^1].
 
 ### Setup
 
-First, install the dependencies.
+First, install the dependencies:
 
 ```
 pip install -r requirements.txt
@@ -19,6 +19,28 @@ Install [`ffmpeg`](https://ffmpeg.org/):
 brew install ffmpeg
 ```
 
+Next, download the Whisper PyTorch checkpoint and convert the weights to the MLX format. For example, to convert the `tiny` model use:
+
+```
+python convert.py --torch-name-or-path tiny --mlx-path mlx_models/tiny
+```
+
+Note you can also convert a local PyTorch checkpoint which is in the original OpenAI format.
+
+To generate a 4-bit quantized model, use `-q`. For a full list of options:
+
+```
+python convert.py --help
+```
+
+By default, the conversion script will make the directory `mlx_models/tiny` and save
+the converted `weights.npz` and `config.json` there.
+
+> [!TIP]
+> Alternatively, you can also download a few converted checkpoints from the
+> [MLX Community](https://huggingface.co/mlx-community) organization on Hugging
+> Face and skip the conversion step.
+
 ### Run
 
 Transcribe audio with: