Closed adityarajsahu closed 3 months ago
yeah, having the same error
Same also having that error
I had the same error on Colab(when running get_pretrained), but when I added two lines in requirement.txt , it seems working (But now I am running on local, not Colab). plz anyone add these two lines in requirement.txt and try on Colab
torchvision==0.16.0 torchtext==0.16.0
Yes, it works in colab also. Thanks a lot
(I entered 2 lines:
!pip install torchvision==0.16.0 !pip install torchtext==0.16.0
Between first and second block of code)
@KMOSNU thanks, it works
When I am running the following code ` import torchaudio from audiocraft.models import AudioGen from audiocraft.data.audio import audio_write
model = AudioGen.get_pretrained('facebook/audiogen-medium') model.set_generation_params(duration=5) # generate 5 seconds. descriptions = ['dog barking', 'sirenes of an emergency vehicule', 'footsteps in a corridor'] wav = model.generate(descriptions) # generates 3 samples.
for idx, one_wav in enumerate(wav):
Will save under {idx}.wav, with loudness normalization at -14 db LUFS.
`
locally I am getting the following error
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 14.00 MiB. GPU 0 has a total capacty of 3.81 GiB of which 7.75 MiB is free. Including non-PyTorch memory, this process has 3.79 GiB memory in use. Of the allocated memory 3.09 GiB is allocated by PyTorch, and 9.11 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF
and when running on colab I am getting the following error
ValueError: Could not find the operator torchvision::nms. Please make sure you have already registered the operator and (if registered from C++) loaded it via torch.ops.load_library
How to fix these issues?