Get error in WSL2 with CUDA

[cnjack]

import torch
import ChatTTS
from IPython.display import Audio

chat = ChatTTS.Chat()
chat.load_models()

texts = ["你好啊,我是你的智能助手",]

wavs = chat.infer(texts, use_decoder=True)

Audio(wavs[0], rate=24_000, autoplay=True)

get the error:

python app.py
INFO:ChatTTS.core:Load from cache: /root/.cache/huggingface/hub/models--2Noise--ChatTTS/snapshots/c0aa9139945a4d7bb1c84f07785db576f2bb1bfa
INFO:ChatTTS.core:use cuda:0
INFO:ChatTTS.core:vocos loaded.
INFO:ChatTTS.core:dvae loaded.
INFO:ChatTTS.core:gpt loaded.
INFO:ChatTTS.core:decoder loaded.
INFO:ChatTTS.core:tokenizer loaded.
INFO:ChatTTS.core:All initialized.
INFO:ChatTTS.core:All initialized.
  5%|███████▋                                                                                                                                                    | 19/384 [00:00<00:11, 31.67it/s]
  8%|███████████▉                                                                                                                                              | 158/2048 [00:02<00:24, 75.72it/s]
/root/anaconda3/envs/chatts/lib/python3.11/site-packages/torch/nn/modules/conv.py:306: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
  return F.conv1d(input, weight, bias, self.stride,

[iorzt]

seems related? could you try? https://github.com/pytorch/pytorch/issues/121834

[gaohaozhang]

import torch
import ChatTTS
from IPython.display import Audio

chat = ChatTTS.Chat()
chat.load_models()

texts = ["你好啊,我是你的智能助手",]

wavs = chat.infer(texts, use_decoder=True)

Audio(wavs[0], rate=24_000, autoplay=True)

get the error:

python app.py
INFO:ChatTTS.core:Load from cache: /root/.cache/huggingface/hub/models--2Noise--ChatTTS/snapshots/c0aa9139945a4d7bb1c84f07785db576f2bb1bfa
INFO:ChatTTS.core:use cuda:0
INFO:ChatTTS.core:vocos loaded.
INFO:ChatTTS.core:dvae loaded.
INFO:ChatTTS.core:gpt loaded.
INFO:ChatTTS.core:decoder loaded.
INFO:ChatTTS.core:tokenizer loaded.
INFO:ChatTTS.core:All initialized.
INFO:ChatTTS.core:All initialized.
  5%|███████▋                                                                                                                                                    | 19/384 [00:00<00:11, 31.67it/s]
  8%|███████████▉                                                                                                                                              | 158/2048 [00:02<00:24, 75.72it/s]
/root/anaconda3/envs/chatts/lib/python3.11/site-packages/torch/nn/modules/conv.py:306: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
  return F.conv1d(input, weight, bias, self.stride,

你好，请问您这个问题解决了吗

[github-actions[bot]]

This issue was closed because it has been inactive for 15 days since being marked as stale.