Update webui.py with consistent model name of CosyVoice3-0.5B and add installation for AMD ROCm GPU

README.md

@@ -99,9 +99,26 @@
     ``` sh
     conda create -n cosyvoice -y python=3.10
     conda activate cosyvoice
+    ```
+
+#### Install with NVIDIA CUDA
+
+    ``` sh
     pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
+    ```
+
+#### Install with AMD ROCm
 
-    # If you encounter sox compatibility issues
+Install PyTorch with ROCm
+
+    ``` sh
+    pip3 install torch torchvision --index-url https://download.pytorch.org/whl/rocm6.4
+    pip install -r requirements-rocm.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
+    ```
+
+If you encounter sox compatibility issues
+
+    ``` sh
     # ubuntu
     sudo apt-get install sox libsox-dev
     # centos

requirements-rocm.txt

@@ -0,0 +1,36 @@
+conformer==0.3.2
+deepspeed==0.15.1; sys_platform == 'linux'
+diffusers==0.29.0
+fastapi==0.115.6
+fastapi-cli==0.0.4
+gdown==5.1.0
+gradio==5.4.0
+grpcio==1.57.0
+grpcio-tools==1.57.0
+hydra-core==1.3.2
+HyperPyYAML==1.2.2
+inflect==7.3.1
+librosa==0.10.2
+lightning==2.2.4
+matplotlib==3.7.5
+modelscope==1.20.0
+networkx==3.1
+numpy==1.26.4
+omegaconf==2.3.0
+onnx==1.16.0
+onnxruntime-gpu==1.18.0; sys_platform == 'linux'
+onnxruntime==1.18.0; sys_platform == 'darwin' or sys_platform == 'win32'
+openai-whisper==20231117
+protobuf==4.25
+pyarrow==18.1.0
+pydantic==2.7.0
+pyworld==0.3.4
+rich==13.7.1
+soundfile==0.12.1
+tensorboard==2.14.0
+torchcodec==0.9.1
+transformers==4.51.3
+x-transformers==2.11.24
+uvicorn==0.30.0
+wetext==0.0.4
+wget==3.2

webui.py

@@ -167,7 +167,7 @@ def main():
                         default=8000)
     parser.add_argument('--model_dir',
                         type=str,
-                        default='pretrained_models/CosyVoice3-0.5B',
+                        default='pretrained_models/Fun-CosyVoice3-0.5B',
                         help='local path or modelscope repo id')
     args = parser.parse_args()
     cosyvoice = AutoModel(model_dir=args.model_dir)