Ünal Ege Gaznepoğlu

> Well... > This chunk seems to work for me ... > > If I have a singa that i transform like this > > ```python > my_singal = ......

Hi, I am having a similar problem with the Respeaker-4-mic-array for Raspberry Pi, though not with the "reference" mics but with the recordings. Is there any active development/troubleshooting going on?...

@JaPhoton this solved my problem. Thanks a lot!

I have forked this repository and applied the necessary changes there. Then if I recall correctly, things worked like a charm. If you click on my profile you should be...

I experienced this too. I feel that different parameter configurations cause this problem (e.g. setting a FFT length which is not a power of 2). I'll invest few hours to...

I have also been experiencing this issue, and after numerous attempts, managed to get a full execution without any 'refusing to run' errors. I created a shell script in the...

I came up with another hacky way to do this while leveraging all the convenience of the `MultiResolutionSTFT` class is to monkey-patch the `auraloss.freq.apply_reduction` function in the following way: `auraloss.freq.apply_reduction...

@csteinmetz1 Also, I noticed that for spectral convergence loss, despite the option `reduction=None, we nevertheless get a reduced result, because it has been implemented like this: ```python return torch.norm(y_mag -...

@TParcollet Here is a minimal working (or in this case crashing) example: ```python import torch import torch.nn as nn from speechbrain.lobes.models.transformer.TransformerASR import TransformerASR import random # Instantiate the TransformerASR model...

I had this error while training a model using `DistributedDataParallel` on 2 GPUs. Could it be that initial data sampler does the padding relative to the complete batch size, but...