Update README

README.md

@@ -43,12 +43,19 @@ If you are a Windows user (tested with win>=10) you can install directly via the
 
 - Python 3.9, PyTorch 2.0.1, CUDA 11
 - Python 3.10.13, PyTorch 2.1.2, CUDA 12.3
-- Python 3.9, PyTorch 2.3.0.dev20240122, macOS 14.3 (Apple Silicon, MPS)
+- Python 3.9, PyTorch 2.3.0.dev20240122, macOS 14.3 (Apple silicon, GPU)
 
 _Note: numba==0.56.4 require py<3.11_
 
 ### For Mac Users
-If you are a Mac user, please install by using the following commands:
+If you are a Mac user, make sure you meet the following conditions for training and inferencing with GPU: 
+- Mac computers with Apple silicon or AMD GPUs
+- macOS 12.3 or later
+- Xcode command-line tools installed by running `xcode-select --install`
+
+_Other Macs can do inference with CPU only._
+
+Then install by using the following commands:
 #### Create  Environment
 ```bash
 conda create -n GPTSoVits python=3.9
@@ -60,7 +67,7 @@ pip install -r requirements.txt
 pip uninstall torch torchaudio
 pip3 install --pre torch torchaudio --index-url https://download.pytorch.org/whl/nightly/cpu
 ```
-_Note: For preprocessing with UVR5, it is recommended to [download the original project GUI](https://github.com/Anjok07/ultimatevocalremovergui) and select GPU for operation. Additionally, there may be memory leak issues when using Mac for inference, restarting the inference webUI can release the memory._
+_Note: For preprocessing with UVR5, it is recommended to [download the original project GUI](https://github.com/Anjok07/ultimatevocalremovergui) and select "GPU Conversion". Additionally, there might be memory leak issues, especially during inference. Restarting the inference webUI can help._
 ### Quick Install with Conda
 
 ```bash