报错:WARNING:ChatTTS.utils.gpu_utils:No GPU found, use CPU instead

[gggggwen]

[shirubei]

装了gpu版的pytorch了吗

[dyfqpl1]

遇到了同样的问题，怎么解决啊

[KiwiHana]

WARNING:ChatTTS.utils.gpu_utils:No GPU found, use CPU instead INFO:ChatTTS.core:use cpu WARNING:ChatTTS.core:vocos not initialized. WARNING:ChatTTS.core:gpt not initialized. WARNING:ChatTTS.core:tokenizer not initialized. WARNING:ChatTTS.core:dvae not initialized. WARNING:ChatTTS.core:vocos not initialized. WARNING:ChatTTS.core:gpt not initialized. WARNING:ChatTTS.core:tokenizer not initialized. WARNING:ChatTTS.core:decoder not initialized. Traceback (most recent call last): File "C:\Users\solution\run_chattts.py", line 13, in wavs = chat.infer(texts, use_decoder=True) File "C:\Users\hu\Miniconda3\envs\chattts\lib\site-packages\ChatTTS\core.py", line 95, in infer assert self.check_model(use_decoder=use_decoder) AssertionError

[johne5s]

Have you installed the gpu version of pytorch?

I had the same thing. I needed to install the torch GPU version from the torch website. https://pytorch.org/get-started/previous-versions/

i have a 3090, and used these commands. pip uninstall torch pip install torch==2.2.2 torchvision==0.17.2 torchaudio==2.2.2 --index-url https://download.pytorch.org/whl/cu118

[shinedlc]

1、Check CUDA version first: nvcc --version 2、Ensure: invidia-smi ≥ nvcc --version ≥ Pytorch cudatoolkit version required 3、Test: $ python

import torch print(torch.cuda.is_available()) True

[KiwiHana]

I don't have NV DGPU on device.

1、Check CUDA version first: nvcc --version 2、Ensure: invidia-smi ≥ nvcc --version ≥ Pytorch cudatoolkit version required 3、Test: $ python

import torch print(torch.cuda.is_available()) True

[yuanhaoyang2004]

我的设备上没有 NV DGPU。

1、首先检查CUDA版本：nvcc--version 2、确保：invidia-smi ≥nvcc --version ≥ 需要Pytorch cudatoolkit版本 3、测试：$python

导入割炬打印（torch.cuda.is_available（）） True

me too

[fsea]

1、pip uninstall -y torch torchaudio 2、pip install torch torchaudio

[hexf00]

nvcc -V
python

print(torch.__version__)
print(torch.cuda.is_available())
print(torch.cuda.device_count())
print(torch.version.cuda)

版本一致后可以启用GPU，4060 比 7945hx 快 3 倍左右

[KiwiHana]

1、pip uninstall -y torch torchaudio 2、pip install torch torchaudio

torch 2.3.1+cpu torchaudio 2.3.1+cpu

(chattts) C:\digtal_human\ChatTTS>python run_chattts.py WARNING:ChatTTS.utils.gpu_utils:No GPU found, use CPU instead INFO:ChatTTS.core:use cpu WARNING:ChatTTS.core:vocos not initialized. WARNING:ChatTTS.core:gpt not initialized. WARNING:ChatTTS.core:tokenizer not initialized. WARNING:ChatTTS.core:dvae not initialized. WARNING:ChatTTS.core:vocos not initialized. WARNING:ChatTTS.core:gpt not initialized. WARNING:ChatTTS.core:tokenizer not initialized. WARNING:ChatTTS.core:decoder not initialized. Traceback (most recent call last): File "C:\Users\sutai\Desktop\digtal_human\ChatTTS\run_chattts.py", line 20, in wavs = chat.infer(texts, use_decoder=True) File "C:\Users\sutai.conda\envs\chattts\lib\site-packages\ChatTTS\core.py", line 95, in infer assert self.check_model(use_decoder=use_decoder) AssertionError