ADD-eNavarro

Looking forward for this to be fixed, since I find myself in the same situation. Thanks for your great work, by the way!

Great, thank you! Eager to try them!

Still didn't work for me: Message= Unknown builtin op: torchaudio::sox_effects_apply_effects_tensor. Could not find any similar ops to torchaudio::sox_effects_apply_effects_tensor. This op may not exist or may not be currently supported in...

Yes, my code is as in the example: import torch # This is 1.8.0 import torchaudio # This is 0.8.0 wav2mel = torch.jit.load(r"yistLin dvector\wav2mel.pt") # Error

Exactly those (sorry, updated the comment a bit too late)

I get an error in: wav2mel = torch.jit.script(wav2mel) Message= undefined value torch: File "***\AppData\Roaming\Python\Python37\site-packages\torchaudio\_internal\module_utils.py", line 151 >>> assert sample_rate == 8000 """ return torch.ops.torchaudio.sox_effects_apply_effects_tensor( ~~~~~ torch.Tensor: wav_tensor, _ = apply_effects_tensor(wav_tensor,...

You're right, I'm working on Windows. Sox is installed, sox_io won't install on Windows. That might be the cause indeed. I will look into it too, but it would be...

Hello Mr. Gibby, did you manage to make CSCore work on .NET Standard then?

So, here's the thing: I have trained a VITS model (from phonemes and for spanish) in an A100 GPU, and now I'm trying to export it to onnx format, since...

I add a few more prints here and there to follow the shapes being used. In TTS\TTS\tts\layers\vits\networks.py (class TextEncoder, function forward) I have: - Inputs: X: torch.Size([1, 128]) X_LENGTHS: torch.Size([1,...