search

CircuitCM / RVC-inference

High performance RVC inferencing, intended for multiple instances in memory at once. Also includes the latest pitch estimator RMVPE, Python 3.8-3.11 compatible, pip installable, memory + performance improvements in the pipeline and model usage.
MIT License
19 stars 3 forks source link

Throws an error if not using CUDA. #3

Open Lunatunny opened 5 months ago

Lunatunny commented 5 months ago

I'm trying to do the example in the readme with my CPU and I get the below error

Traceback (most recent call last):
  File "C:\Users\kuzum\git\pth_inferer\infer_and_serve.py", line 2, in <module>
    from inferrvc import RVC
  File "C:\Program Files\Python311\Lib\site-packages\inferrvc\__init__.py", line 10, in <module>
    from .modules import RVC,ResampleCache,download_models,load_torchaudio
  File "C:\Program Files\Python311\Lib\site-packages\inferrvc\modules.py", line 19, in <module>
    from .pipeline import Pipeline
  File "C:\Program Files\Python311\Lib\site-packages\inferrvc\pipeline.py", line 31, in <module>
    bh,ah=torch.from_numpy(bh).to(_gpu,non_blocking=True),torch.from_numpy(ah).to(_gpu,non_blocking=True)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\kuzum\AppData\Roaming\Python\Python311\site-packages\torch\cuda\__init__.py", line 293, in _lazy_init
    raise AssertionError("Torch not compiled with CUDA enabled")

Presumably from this line https://github.com/CircuitCM/RVC-inference/blob/dea0ec905b79d6e2648369bcd7ba5aca79d82785/inferrvc/pipeline.py#L31

CircuitCM commented 5 months ago

Hi thanks, I'll resolve when I have a moment this week.