KinWaiCheuk

May I know if you are using `CQT1992`? It is an expected behavior especially when you include low-frequency bins. Because for CQT, in order to maintain a constant Q (the...

At first glance, it seems this error is related to PyTorch version, rather than nnAudio. Which PyTorch version are you using? Could you please share me the code for converting...

I ran a quick test on my computer with the following code, and I can obtain the onnx file successfully. ```python from nnAudio.Spectrogram import STFT import torch dummy_input = torch.randn(4,44100)...

You are right, when trying to export `iSTFT` to onnx, it will result in an error message: > RuntimeError: Exporting the operator col2im to ONNX opset version 12 is not...

I need to double check first. Unfortunately it seems log frequency scale is not invertible mathematically. Only the STFT with the original frequency bin (k) scale is invertible, the moment...

Although nnAudio does not support an extra channel dimension, there is a quick workaround for it. Assume that your signal is of the sample `(B, C, N)`, where **B**, **C**,...

Hi tasercake, I was also looking at it since few days ago. Gradient descend does not work well in this case since we are dealing with a sparse matrix (The...

Hi tasercake, after a second thought, I don't think NNLS is the right way to go, since it does not provide us the inverse matrix. Therefore we need to keep...

> you also get quite decent results by just transposing the mel filterbank That is interesting to know. I have thought of that before, but it seemed too good to...

It is not invertible at the moment same as the Mel-spectrogram. @tasercake attempted to implement the invertible Mel-spectrogram previously, but it took longer than libraosa to converge. https://github.com/KinWaiCheuk/nnAudio/issues/57 Knowing how...