mirror of
https://github.com/RevLayDust/RLD-UVR-Opt.git
synced 2026-11-20 13:07:58 +09:00
85 lines
4.7 KiB
Plaintext
85 lines
4.7 KiB
Plaintext
(venv) PS D:\AI\Ultimate Vocal Remover> python -m uvr_cli run -a "D:\AI\UVR\Experiments\exp_1\edited_remixed_audio-2.wav" -m UVR-MDX-NET-Inst_HQ_4.onnx -p fp32 -d cpu --segment-size 4000 --overlap 0.25 -o D:\AI\UVR\Experiments\exp_1\out
|
|
Resolving model: UVR-MDX-NET-Inst_HQ_4.onnx (MDX-Net)
|
|
Separating : edited_remixed_audio-2.wav
|
|
Precision : Ultra Quality (FP32)
|
|
Output folder : D:\AI\UVR\Experiments\exp_1\out
|
|
|
|
[!] Output file(s) already exist:
|
|
-> edited_remixed_audio-2_(Instrumental).wav
|
|
-> edited_remixed_audio-2_(Vocals).wav
|
|
|
|
Overwrite? [Y/N]: y
|
|
[DIAGNOSTIC] === SeperateMDX.seperate Start ===
|
|
[DIAGNOSTIC] Initial GPU Alloc: 0.00 MB, Reserved: 0.00 MB
|
|
[DIAGNOSTIC] Cache keys currently stored: []
|
|
[DIAGNOSTIC] get_model lookup: D:\AI\Ultimate Vocal Remover\models\MDX_Net_Models\UVR-MDX-NET-Inst_HQ_4.onnx -> normalized: D:\AI\Ultimate Vocal Remover\models\MDX_Net_Models\UVR-MDX-NET-Inst_HQ_4.onnx
|
|
[DIAGNOSTIC] get_model Cache Miss for: D:\AI\Ultimate Vocal Remover\models\MDX_Net_Models\UVR-MDX-NET-Inst_HQ_4.onnx
|
|
Model Cache Store: Resident model cached UVR-MDX-NET-Inst_HQ_4.onnx (precision: Ultra Quality (FP32))
|
|
[PRECISION] === Runtime Precision Report ===
|
|
[PRECISION] requested_mode: FP32
|
|
[PRECISION] effective_mode: FP32
|
|
[PRECISION] model_type: ONNX
|
|
[PRECISION] execution_provider: ['CPUExecutionProvider']
|
|
[PRECISION] onnx_input_type: tensor(float)
|
|
[PRECISION] onnx_output_type: tensor(float)
|
|
[PRECISION] active_providers: ['CPUExecutionProvider']
|
|
[PRECISION] [OK] Precision applied correctly: FP32
|
|
[PRECISION] ==============================
|
|
[UVR Core] Done!
|
|
|
|
[UVR Core] Running inference...
|
|
Traceback (most recent call last):
|
|
File "<frozen runpy>", line 198, in _run_module_as_main
|
|
File "<frozen runpy>", line 88, in _run_code
|
|
File "D:\AI\Ultimate Vocal Remover\uvr_cli\__main__.py", line 6, in <module>
|
|
main()
|
|
File "D:\AI\Ultimate Vocal Remover\uvr_cli\cli.py", line 330, in main
|
|
sys.exit(handle_run(args))
|
|
^^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\uvr_cli\cli.py", line 142, in handle_run
|
|
stems, is_valid = execute_inference(
|
|
^^^^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\uvr_cli\runner.py", line 165, in execute_inference
|
|
separator.seperate()
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 940, in seperate
|
|
source = self.demix(mix)
|
|
^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 1068, in demix
|
|
stream_transfer = torch.cuda.Stream(device=self.device)
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\venv\Lib\site-packages\torch\cuda\streams.py", line 45, in __new__
|
|
with torch.cuda.device(device):
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 940, in seperate
|
|
source = self.demix(mix)
|
|
^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 1068, in demix
|
|
stream_transfer = torch.cuda.Stream(device=self.device)
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\venv\Lib\site-packages\torch\cuda\streams.py", line 45 File "D:\AI\Ultimate Vocal Remover\separate.py", line 940, in seperate
|
|
source = self.demix(mix)
|
|
^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 1068, in demix
|
|
stream_transfer = torch.cuda.Stream(device=self.device)
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 940, in seperate
|
|
source = self.demix(mix)
|
|
^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 1068, in demix
|
|
stream_transfer = torch.cuda.Stream(device=self.device)
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 940, in seperate
|
|
source = self.demix(mix)
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 940, in seperate
|
|
source = self.demix(mix)
|
|
^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\separate.py", line 1068, in demix
|
|
stream_transfer = torch.cuda.Stream(device=self.device)
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\venv\Lib\site-packages\torch\cuda\streams.py", line 45, in __new__
|
|
with torch.cuda.device(device):
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\venv\Lib\site-packages\torch\cuda\__init__.py", line 600, in __init__
|
|
self.idx = _get_device_index(device, optional=True)
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
File "D:\AI\Ultimate Vocal Remover\venv\Lib\site-packages\torch\cuda\_utils.py", line 542, in _get_device_index
|
|
raise ValueError(f"Expected a cuda device, but got: {device}")
|
|
ValueError: Expected a cuda device, but got: cpu
|
|
[DIAGNOSTIC] === SeperateAttributes Destructor Called for: UVR-MDX-NET-Inst_HQ_4 === |