-
-
Notifications
You must be signed in to change notification settings - Fork 272
Description
Hi, I cannot even get the example to work on my machine... What is going on?
Steps to reproduce
- Install MacOS 26.1 on Mac Mini M4
- Install xcode command line tools
- Create Python venv because it shouldn't mess with system libraries.
- Install mlx-audio with pip according to guide here in venv.
- Try to run mlx-audio. It crashes and wants more dependencies
- Add needed dependencies
- Run mlx-audio again. It doesnt work.
Error:
(venv) traace@Mac-mini-von-traace myproject % mlx_audio.tts.generate --text "Hello, world" /Users/traace/myproject/venv/lib/python3.9/site-packages/urllib3/__init__.py:35: NotOpenSSLWarning: urllib3 v2 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020 warnings.warn( Fetching 63 files: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████| 63/63 [00:00<00:00, 48798.00it/s] Error loading model: unsupported operand type(s) for |: 'nb_type_0' and 'type' Traceback (most recent call last): File "/Users/traace/myproject/venv/lib/python3.9/site-packages/mlx_audio/tts/generate.py", line 262, in generate_audio model = load_model(model_path=model) File "/Users/traace/myproject/venv/lib/python3.9/site-packages/mlx_audio/tts/utils.py", line 241, in load_model model_class, model_type = get_model_and_args( File "/Users/traace/myproject/venv/lib/python3.9/site-packages/mlx_audio/tts/utils.py", line 123, in get_model_and_args arch = importlib.import_module(f"mlx_audio.tts.models.{model_type}") File "/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/importlib/__init__.py", line 127, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "<frozen importlib._bootstrap>", line 1030, in _gcd_import File "<frozen importlib._bootstrap>", line 1007, in _find_and_load File "<frozen importlib._bootstrap>", line 986, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 680, in _load_unlocked File "<frozen importlib._bootstrap_external>", line 850, in exec_module File "<frozen importlib._bootstrap>", line 228, in _call_with_frames_removed File "/Users/traace/myproject/venv/lib/python3.9/site-packages/mlx_audio/tts/models/kokoro/__init__.py", line 1, in <module> from .kokoro import Model, ModelConfig File "/Users/traace/myproject/venv/lib/python3.9/site-packages/mlx_audio/tts/models/kokoro/kokoro.py", line 13, in <module> from .istftnet import Decoder File "/Users/traace/myproject/venv/lib/python3.9/site-packages/mlx_audio/tts/models/kokoro/istftnet.py", line 8, in <module> from mlx_audio.utils import istft, stft File "/Users/traace/myproject/venv/lib/python3.9/site-packages/mlx_audio/utils.py", line 11, in <module> from mlx_audio.dsp import ( File "/Users/traace/myproject/venv/lib/python3.9/site-packages/mlx_audio/dsp.py", line 72, in <module> window: mx.array | str = "hann", TypeError: unsupported operand type(s) for |: 'nb_type_0' and 'type'