Separatee
commented
4 months ago 有可能是没有正确的onnx版本来调用gpu，尝试使用这个命令
/path/to/your/python -m pip install onnxruntime-gpu -i https://pypi.tuna.tsinghua.edu.cn/simple并且请反复检查一下cuda版本是否兼容，或许可以尝试重装新版驱动，并且在安装时选择清洁安装
SapphireLab
C:\Users\xxx\AppData\Roaming\Python\Python39\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py:69: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider' warnings.warn( C:\Users\leon\AppData\Roaming\Python\Python39\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py:69: UserWarning: Specified provider 'DmlExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider' warnings.warn( Processing: 0%| | 0/17 [00:00<?, ?it/s]D:\BaiduNetdiskDownload\GPT-SoVITS-beta0217fix3\tools\uvr5\mdxnet.py:164: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\utils\tensor_new.cpp:277.) mix_waves = torch.tensor(mix_waves, dtype=torch.float32).to(cpu)