diff --git a/README.md b/README.md
index dfbbb774..38a052d8 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,9 @@ Check out the [example](example.ipynb) notebook for a quick start. Or open it in
## Prepare the environment
-As we all know, the dependencies of an AI project are always a mess. Here is how I prepare the environment for this project, by conda:
+As we all know, the dependencies of an AI project are always a mess. Here is how I prepare the environment for this project:
+
+Conda (Linux)
```
conda install python=3.10
@@ -16,6 +18,18 @@ conda install pytorch=2.1 torchvision torchaudio pytorch-lightning pytorch-cuda=
conda install ffmpeg=6.1.1 -c conda-forge
```
+
+
+MacOS
+
+```
+brew install ffmpeg
+pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+pip3 install pytorch-lightning
+pip3 install GPT-SoVITS-Infer
+```
+
+
You can also try to prepare the environment with cpu only options, which should work, but I have not tested it yet.
After the environment is ready, you can install the package by pip:
diff --git a/src/gpt_sovits/infer/worker.py b/src/gpt_sovits/infer/worker.py
index 7074e136..633b4531 100644
--- a/src/gpt_sovits/infer/worker.py
+++ b/src/gpt_sovits/infer/worker.py
@@ -105,6 +105,8 @@ def __init__(
if device is None:
if torch.cuda.is_available():
device = "cuda"
+ elif torch.backends.mps.is_available():
+ device = "mps"
else:
device = "cpu"
self.device = device