bug描述 Describe the Bug

环境：
python：3.8.16
cudatoolkit：11.6.0
cudnn：8.4.1.50
paddlepaddle-gpu：2.5.0rc1.post116（2.4.2也是同样的问题）
paddlespeech：1.4.1

运行命令：
paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" --output output.wav

WARNING: OMP_NUM_THREADS set to 15, not 1. The computation speed will not be optimized if you use data parallel. It will fail if this PaddlePaddle binary is compiled with OpenBlas since OpenBlas does not support multi-threads.
PLEASE USE OMP_NUM_THREADS WISELY.
/root/autodl-tmp/conda/envs/metahuman/lib/python3.8/site-packages/_distutils_hack/__init__.py:33: UserWarning: Setuptools is replacing distutils.
  warnings.warn("Setuptools is replacing distutils.")
W0615 23:36:05.325722 11564 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 8.6, Driver API Version: 12.0, Runtime API Version: 11.6
W0615 23:36:05.330312 11564 gpu_resources.cc:149] device: 0, cuDNN Version: 8.4.
I0615 23:36:06.536566 11564 eager_method.cc:139] Warning:: 0D Tensor cannot be used as 'Tensor.numpy()[0]' . In order to avoid this problem, 0D Tensor will be changed to 1D numpy currently, but it's not correct and will be removed in release 2.6. For Tensor contain only one element, Please modify  'Tensor.numpy()[0]' to 'float(Tensor)' as soon as possible, otherwise 'Tensor.numpy()[0]' will raise error in release 2.6.
I0615 23:36:06.536931 11564 eager_method.cc:139] Warning:: 0D Tensor cannot be used as 'Tensor.numpy()[0]' . In order to avoid this problem, 0D Tensor will be changed to 1D numpy currently, but it's not correct and will be removed in release 2.6. For Tensor contain only one element, Please modify  'Tensor.numpy()[0]' to 'float(Tensor)' as soon as possible, otherwise 'Tensor.numpy()[0]' will raise error in release 2.6.
OSError: (External) CUBLAS error(7). 
  [Hint: Please search for the error code(7) on website (https://docs.nvidia.com/cuda/cublas/index.html#cublasstatus_t) to get Nvidia's official solution and advice about CUBLAS Error.] (at ../paddle/phi/kernels/funcs/blas/blas_impl.cu.h:37)

其他补充信息 Additional Supplementary Information

全安装过程（只有这几步）：

conda install paddlepaddle-gpu==2.5.0rc1 cudatoolkit=11.6 -c https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/Paddle/ -c conda-forge
pip install pytest-runner
pip install paddlespeech
pip install librosa==0.10.0