Preprocessing Error on CPU

Hi. I'm trying to preprocess audio data for my test model -- with RMVPE, hubertsoft, and nsf_hifigan -- since there aren't any new sample models I could see. I'm running Miniconda 3 using Python 3.8 on Windows 10 with CPU versions of torch 2.0.0 and torchaudio 2.0.1 installed. I have an NVIDIA GPU (GTX1050), but I believe 4GB of VRAM isn't sufficient to run audio projects like this, or any AI project at all. It seems from my understanding that torch is trying to load a CUDA device when I only installed the CPU versions. Here's my traceback (edited for anonymity): > (_ddsp-miniconda1) D:\My Downloads\AI Audio Projects\DDSP-SVC-5.0>python preprocess.py -c configs/combsub.yaml > 2025-01-05 17:56:13 | INFO | fairseq.tasks.text_to_speech | Please install tensorboardX: pip install tensorboardX > Traceback (most recent call last): > File "preprocess.py", line 159, in <module> > f0_extractor = F0_Extractor( > File "D:\My Downloads\AI Audio Projects\DDSP-SVC-5.0\ddsp\vocoder.py", line 37, in __init__ > F0_KERNEL['rmvpe'] = RMVPE('pretrain/rmvpe/model.pt', hop_length=160) > File "D:\My Downloads\AI Audio Projects\DDSP-SVC-5.0\encoder\rmvpe\inference.py", line 14, in __init__ > ckpt = torch.load(model_path) > File "D:\Programs\Miniconda3\envs\_ddsp-miniconda1\lib\site-packages\torch\serialization.py", line 809, in load > return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) > File "D:\Programs\Miniconda3\envs\_ddsp-miniconda1\lib\site-packages\torch\serialization.py", line 1172, in _load > result = unpickler.load() > File "D:\Programs\Miniconda3\envs\_ddsp-miniconda1\lib\site-packages\torch\serialization.py", line 1142, in persistent_load > typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location)) > File "D:\Programs\Miniconda3\envs\_ddsp-miniconda1\lib\site-packages\torch\serialization.py", line 1116, in load_tensor > wrap_storage=restore_location(storage, location), > File "D:\Programs\Miniconda3\envs\_ddsp-miniconda1\lib\site-packages\torch\serialization.py", line 217, in default_restore_location > result = fn(storage, location) > File "D:\Programs\Miniconda3\envs\_ddsp-miniconda1\lib\site-packages\torch\serialization.py", line 182, in _cuda_deserialize << (I don't know where _that_ came from.) > device = validate_cuda_device(location) > File "D:\Programs\Miniconda3\envs\_ddsp-miniconda1\lib\site-packages\torch\serialization.py", line 166, in validate_cuda_device > raise RuntimeError('Attempting to deserialize object on a CUDA ' > RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU. How do I map the torch.load function to CPU, or what might have I done wrong? I do apologize if I missed any FAQs, closed issues, or general traditions in GitHub; it's my first time ever opening an issue. Thank you for reading, and have a good (rest of your) day!