zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-31 11:54:37 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add notes about conversion

Browse Source
This commit is contained in:
bofenghuang 2023-12-29 17:20:41 +01:00
parent 27e9c3de06
commit fcacc57950
1 changed files with 22 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
whisper/README.md
View File

@ -6,7 +6,7 @@ parameters[^1].
### Setup
First, install the dependencies.
First, install the dependencies:
```
pip install -r requirements.txt
@ -19,6 +19,27 @@ Install [`ffmpeg`](https://ffmpeg.org/):
brew install ffmpeg
```
Next, download the Whisper PyTorch checkpoint and convert the weights to MLX format:
```
# Take the "tiny" model as an example. Note that you can also convert a local PyTorch checkpoint in OpenAI's format.
python convert.py --torch-name-or-path tiny --mlx-path mlx_models/tiny
```
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: