Stem separation server don't install models on win11

[TonatiuhWarrior]

******* while trying to install the server + models through the feedback app Settings\Stem Splitter I got the following error:

Traceback (most recent call last):
File "C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\src\run_roformer.py", line 82, in
sys.exit(main())
^^^^^^
File "C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\src\run_roformer.py", line 55, in main
from audio_separator.separator import Separator
File "C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\audio_separator\separator__init__.py", line 1, in
from .separator import Separator
File "C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\audio_separator\separator\separator.py", line 27, in
from audio_separator.separator.ensembler import Ensembler
File "C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\audio_separator\separator\ensembler.py", line 3, in
from audio_separator.separator.uvr_lib_v5 import spec_utils
File "C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\audio_separator\separator\uvr_lib_v5\spec_utils.py", line 1, in
import audioread
ModuleNotFoundError: No module named 'audioread'
[warmup] bs_roformer_sw: failed: exit 1
[warmup] whisperx: downloading
INFO: 127.0.0.1:52045 - "GET /health HTTP/1.1" 200 OK
INFO: 127.0.0.1:52047 - "GET /health HTTP/1.1" 200 OK
INFO: 127.0.0.1:52049 - "GET /health HTTP/1.1" 200 OK
INFO: 127.0.0.1:52051 - "GET /health HTTP/1.1" 200 OK
INFO: 127.0.0.1:52052 - "GET /health HTTP/1.1" 200 OK
✗ model warmup failed: {'demucs': 'skipped', 'whisperx': 'downloading', 'crepe': 'pending', 'bs_roformer_sw': 'failed', 'whisperx_aligners': {}}

******* manually installed audioread as follows:

python -m pip install audioread --target "C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs"

******* Server is runing, but I am unable to install the models, I get the following error:

C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\pyannote\audio\core\io.py:48: UserWarning:
torchcodec is not installed correctly so built-in audio decoding will fail. Solutions are:
use audio preloaded in-memory as a {'waveform': (channel, time) torch.Tensor, 'sample_rate': int} dictionary;
fix torchcodec installation. Error message was:
Could not load libtorchcodec. Likely causes:

FFmpeg is not properly installed in your environment. We support
versions 4, 5, 6 and 7.
The PyTorch version (2.8.0+cu128) is not compatible with
this version of TorchCodec. Refer to the version compatibility
table:https://github.com/pytorch/torchcodec?tab=readme-ov-file#installing-torchcodec.
Another runtime dependency; see exceptions below.
The following exceptions were raised as we tried to load libtorchcodec:
[start of libtorchcodec loading traceback]
FFmpeg version 7: Could not find module 'C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\torchcodec\libtorchcodec_core7.dll' (or one of its dependencies). Try using the full path with constructor syntax.
FFmpeg version 6: Could not find module 'C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\torchcodec\libtorchcodec_core6.dll' (or one of its dependencies). Try using the full path with constructor syntax.
FFmpeg version 5: Could not find module 'C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\torchcodec\libtorchcodec_core5.dll' (or one of its dependencies). Try using the full path with constructor syntax.
FFmpeg version 4: Could not find module 'C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\torchcodec\libtorchcodec_core4.dll' (or one of its dependencies). Try using the full path with constructor syntax.
[end of libtorchcodec loading traceback].
warnings.warn(
[warmup] whisperx: failed: Requested float16 compute type, but the target device or backend do not support efficient float16 computation.
[warmup] crepe: downloading
C:\Users\Tonatiuh\AppData\Roaming\feedback-desktop\slopsmith-config\demucs-server\pylibs\torch_utils.py:101: UserWarning: expandable_segments not supported on this platform (Triggered internally at C:\actions-runner_work\pytorch\pytorch\pytorch\c10/cuda/CUDAAllocatorConfig.h:35.)
untyped_storage = torch.UntypedStorage(self.size(), device=device)