I am running into this SIGSEGV error each time I use the large model; small will generate the wav file just fine.
python model.py --path weights/ --text "hello world" --model large
Generating semantic tokens...
22%|███████████████████████████████████████▊ | 172/768 [00:01<00:06, 98.38it/s]Early stop at step 173 with token array([10000], dtype=int32)
23%|████████████████████████████████████████ | 173/768 [00:01<00:06, 96.25it/s]
Generating coarse tokens...
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:01<00:00, 5.89it/s]
Generating fine tokens...
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 20.73it/s]
/Users/lawls/Development/github/mlx_bark/.venv/lib/python3.11/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
fish: Job 2, 'python model.py --path weights/…' terminated by signal SIGSEGV (Address boundary error)
/Users/lawls/.pyenv/versions/3.11.7/lib/python3.11/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
I am running into this SIGSEGV error each time I use the large model; small will generate the wav file just fine.