Invalid file: WindowsPath of encodec using Windows OS.

[MartinEesmaa]

Invalid file: WindowsPath of encodec using Windows OS.

[Limeysoda1]

I think I solved this by 'pip install librosa'

[MartinEesmaa]

Thanks @Limeysoda1, but I got a different error. I think maybe issue for PyTorch:

Traceback (most recent call last):
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\Scripts\encodec.exe\__main__.py", line 7, in <module>
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\encodec\__main__.py", line 111, in main
    compressed = compress(model, wav, use_lm=args.lm)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\encodec\compress.py", line 172, in compress
    compress_to_file(model, wav, fo, use_lm=use_lm)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\encodec\compress.py", line 51, in compress_to_file
    frames = model.encode(wav[None])
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\encodec\model.py", line 144, in encode
    encoded_frames.append(self._encode_frame(frame))
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\encodec\model.py", line 161, in _encode_frame
    emb = self.encoder(x)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\encodec\modules\seanet.py", line 144, in forward
    return self.model(x)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\container.py", line 204, in forward
    input = module(input)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\encodec\modules\seanet.py", line 63, in forward
    return self.shortcut(x) + self.block(x)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\encodec\modules\conv.py", line 210, in forward
    return self.conv(x)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\encodec\modules\conv.py", line 120, in forward
    x = self.conv(x)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1208, in _call_impl
    result = forward_call(*input, **kwargs)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\conv.py", line 313, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "C:\Users\marti\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\conv.py", line 309, in _conv_forward
    return F.conv1d(input, weight, bias, self.stride,
RuntimeError: could not create a primitive

Torch versions:

torch                     1.13.0+cu117
torchaudio                0.13.0+cu117

[adefossez]

It is possible that your CPU doesn't support some of the instruction sets required by PyTorch. You should open an issue with PyTorch as this is not really related to the our code.

[MartinEesmaa]

Oh, I see, thank you. I will submit the issue in PyTorch and this repository will be closed my issue by myself.

• Martin Eesmaa