mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-08-08 18:06:37 +08:00
Use pip for mlx data with speech commands (#307)
* update to use pypi mlx data * nit in readme
This commit is contained in:
parent
c6440416a2
commit
c1342b8e89
@ -8,10 +8,6 @@ dataset.
|
|||||||
|
|
||||||
## Pre-requisites
|
## Pre-requisites
|
||||||
|
|
||||||
Follow the [installation
|
|
||||||
instructions](https://ml-explore.github.io/mlx-data/build/html/install.html)
|
|
||||||
for MLX Data.
|
|
||||||
|
|
||||||
Install the remaining python requirements:
|
Install the remaining python requirements:
|
||||||
|
|
||||||
```
|
```
|
||||||
|
@ -1 +1,2 @@
|
|||||||
mlx>=0.0.5
|
mlx
|
||||||
|
mlx-data
|
||||||
|
@ -52,13 +52,13 @@ import whisper
|
|||||||
text = whisper.transcribe(speech_file)["text"]
|
text = whisper.transcribe(speech_file)["text"]
|
||||||
```
|
```
|
||||||
|
|
||||||
Choose the model by setting `hf_path_or_repo`. For example:
|
Choose the model by setting `path_or_hf_repo`. For example:
|
||||||
|
|
||||||
```python
|
```python
|
||||||
result = whisper.transcribe(speech_file, hf_path_or_repo="models/large")
|
result = whisper.transcribe(speech_file, path_or_hf_repo="models/large")
|
||||||
```
|
```
|
||||||
|
|
||||||
This will load the model contained in `models/large`. The `hf_path_or_repo`
|
This will load the model contained in `models/large`. The `path_or_hf_repo`
|
||||||
can also point to an MLX-style Whisper model on the Hugging Face Hub. In this
|
can also point to an MLX-style Whisper model on the Hugging Face Hub. In this
|
||||||
case, the model will be automatically downloaded.
|
case, the model will be automatically downloaded.
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user