zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-06-24 17:31:18 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update whisper readme and requirements

Browse Source
This commit is contained in:
Awni Hannun 2023-12-07 11:15:54 -08:00 committed by Angelos Katharopoulos
parent 54952a0d80
commit 172a60056f
2 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
whisper/README.md
View File

@ -1,10 +1,12 @@
# whisper # whisper
Whisper in MLX. Speech recognition with Whisper in MLX. Whisper is a set of open source speech
recognition models from Open AI, ranging from 39 million to 1.5 billion
parameters[^1].
First install the dependencies: ### Setup
(TODO, MLX install link / command / add to requirements.txt) First, install the dependencies.
``` ```
pip install -r requirements.txt pip install -r requirements.txt
@ -12,12 +14,14 @@ pip install -r requirements.txt
Install [`ffmpeg`](https://ffmpeg.org/): Install [`ffmpeg`](https://ffmpeg.org/):
```bash ```
# on MacOS using Homebrew (https://brew.sh/) # on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg brew install ffmpeg
``` ```
Then transcribe audio with: ### Run
Transcribe audio with:
``` ```
import whisper import whisper
@ -25,3 +29,4 @@ import whisper
text = whisper.transcribe(speech_file)["text"] text = whisper.transcribe(speech_file)["text"]
``` ```
[^1]: Refer to the [arXiv paper](https://arxiv.org/abs/2212.04356), [blog post](https://openai.com/research/whisper), and [code](https://github.com/openai/whisper) for more details.

1
whisper/requirements.txt
View File

@ -1,3 +1,4 @@
mlx
numba numba
numpy numpy
torch torch