【AI翻唱/变声/整合包】有张N卡就能跑！媲美So-VITS却不吃配置，全...

请问这是什么问题

INFO:44k:Loaded checkpoint './logs/44k/D_0.pth' (iteration 0)

./logs/44k/D_0.pth

Traceback (most recent call last):

File "train.py", line 330, in <module>

main()

File "train.py", line 53, in main

mp.spawn(run, nprocs=n_gpus, args=(n_gpus, hps,))

File "/root/miniconda3/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 240, in spawn

return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')

File "/root/miniconda3/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 198, in start_processes

while not context.join():

File "/root/miniconda3/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 160, in join

raise ProcessRaisedException(msg, error_index, failed_process.pid)

torch.multiprocessing.spawn.ProcessRaisedException:

-- Process 0 terminated with the following error:

Traceback (most recent call last):

File "/root/miniconda3/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 69, in _wrap

fn(i, *args)

File "/root/autodl-tmp/so-vits-svc4/train.py", line 138, in run

train_and_evaluate(rank, epoch, hps, [net_g, net_d], [optim_g, optim_d], [scheduler_g, scheduler_d], scaler,

File "/root/autodl-tmp/so-vits-svc4/train.py", line 180, in train_and_evaluate

y_hat_mel = mel_spectrogram_torch(

File "/root/autodl-tmp/so-vits-svc4/modules/mel_processing.py", line 104, in mel_spectrogram_torch

spec = torch.stft(y, n_fft, hop_length=hop_size, win_length=win_size, window=hann_window[wnsize_dtype_device],

File "/root/miniconda3/lib/python3.8/site-packages/torch/functional.py", line 632, in stft

return _VF.stft(input, n_fft, hop_length, win_length, window, # type: ignore[attr-defined]

RuntimeError: cuFFT error: CUFFT_INTERNAL_ERROR

root@autodl-container-c0144d85ef-a83d92c3:~/autodl-tmp/so-vits-svc4#