Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Mac Studio M2 Ultra 64GB #181

Open
michristian opened this issue Mar 9, 2025 · 0 comments
Open

Mac Studio M2 Ultra 64GB #181

michristian opened this issue Mar 9, 2025 · 0 comments

Comments

@michristian
Copy link

I'm using a Mac Studio M2 Ultra with 64GB, which is one of the top Macs, but when I tried using stable-audio-tools to generate a 5-second sound effect, it took over 10 minutes for just 20 steps. And after all that, I couldn't even get the audio output.

Can any other Mac users share if they were able to get it to work?

--

To create a public link, set share=True in launch().
Prompt: glass break
1357556058
/Users/michristian/stable-audio-tools/stable_audio_tools/models/conditioners.py:353: FutureWarning: torch.cuda.amp.autocast(args...) is deprecated. Please use torch.amp.autocast('cuda', args...) instead.
with torch.cuda.amp.autocast(dtype=torch.float16) and torch.set_grad_enabled(self.enable_grad):
/Users/michristian/miniconda3/envs/audio_tools/lib/python3.10/site-packages/torch/amp/autocast_mode.py:266: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
warnings.warn(
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using tokenizers before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
90%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 18/20 [09:40<01:04, 32.26s/it]/Users/michristian/miniconda3/envs/audio_tools/lib/python3.10/site-packages/torchsde/_brownian/brownian_interval.py:599: UserWarning: Should have ta>=t0 but got ta=0.009999999776482582 and t0=0.01.
warnings.warn(f"Should have ta>=t0 but got ta={ta} and t0={self._start}.")
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [10:45<00:00, 32.25s/it]

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant