Cannot Run it on Google Colab!!
I'm trying to run this on Google Colab but getting the following error:
AttributeError Traceback (most recent call last)
in <cell line: 7>()
5 model = AudioGen.get_pretrained('facebook/audiogen-medium')
6 model.set_generation_params(duration=5) # generate 8 seconds.
----> 7 wav = model.generate_unconditional(4) # generates 4 unconditional audio samples
8 descriptions = ['dog barking', 'sirenes of an emergency vehicule', 'footsteps in a corridor']
9 wav = model.generate(descriptions) # generates 3 samples.
AttributeError: 'AudioGen' object has no attribute 'generate_unconditional'
Can anyone help?
Hey
@Prof-Reza
- sorry for the late reply here. Note that the AudioGen class does not contain a generate_unconditional method, on generate and generate_continuation
You can try generating text-conditional samples using the code-snippet provided on the README: https://huggingface.co/facebook/audiogen-medium#audiocraft-usage
Hey @Prof-Reza - sorry for the late reply here. Note that the
AudioGenclass does not contain agenerate_unconditionalmethod, ongenerateandgenerate_continuationYou can try generating text-conditional samples using the code-snippet provided on the README: https://huggingface.co/facebook/audiogen-medium#audiocraft-usage
Hi Sanchit.
I could successfully run this model on a HF space (https://huggingface.co/spaces/TulipAIs/Soundscapes) but recently I keep getting this error whenever trying to generate something:
RuntimeError: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver.
Can you please help with this?