笔记本16G内存 ，显卡为4060 运行 audioldm -t "test"时报错，请问如何解决好

[onunix]

操作系统：ubuntu :
(most recent call last):
File "/home/a/anaconda3/envs/audioldm/bin/audioldm", line 152, in
audioldm = build_model(model_name=args.model_name)
File "/home/a/anaconda3/envs/audioldm/lib/python3.8/site-packages/audioldm/pipeline.py", line 92, in build_model
latent_diffusion = latent_diffusion.to(device)
File "/home/a/anaconda3/envs/audioldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1174, in to
return self._apply(convert)
File "/home/a/anaconda3/envs/audioldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 780, in _apply
module._apply(fn)
File "/home/a/anaconda3/envs/audioldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 854, in _apply
self._buffers[key] = fn(buf)
File "/home/a/anaconda3/envs/audioldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1160, in convert
return t.to(
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 32.00 MiB. GPU 0 has a total capacity of 7.75 GiB of which 14.50 MiB is free. Including non-PyTorch memory, this process has 7.73 GiB memory in use. Of the allocated memory 7.63 GiB is allocated by PyTorch, and 8.70 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)

[haoheliu]

看上去是 GPU 显存（8G）不太够 可以试着生成短一些的音频 比如
audioldm -t "test" -dur 2.5