zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-31 20:04:38 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Improve doc

Browse Source
This commit is contained in:
bofenghuang
2023-12-29 19:09:54 +01:00
parent fcacc57950
commit 95c8459595
2 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
whisper/README.md
View File

@@ -19,14 +19,15 @@ Install [`ffmpeg`](https://ffmpeg.org/):
brew install ffmpeg
```
Next, download the Whisper PyTorch checkpoint and convert the weights to MLX format:
Next, download the Whisper PyTorch checkpoint and convert the weights to the MLX format. For example, to convert the `tiny` model use:
```
# 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:
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

2
whisper/convert.py
View File

@@ -113,7 +113,7 @@ def load_torch_model(
Parameters
----------
name_or_path : str
one of the official model names listed by `whisper.available_models()` or a local Pytorch checkpoint in OpenAI's format
one of the official model names listed by `whisper.available_models()` or a local Pytorch checkpoint which is in the original OpenAI format
download_root: str
path to download the model files; by default, it uses "~/.cache/whisper"