Audio-Super-Resolution

Audio-Super-Resolution copied to clipboard

[REQ] Add a (GH-compliant) license file

2

Hi there, 1st of all thanks for this awesome work ! Since we've 'doxed' it in our [HyMPS project](https://forart.it/HyMPS) (under [AUDIO section](https://github.com/FORARTfe/HyMPS#- ) \ [AI-based category](https://github.com/FORARTfe/HyMPS/blob/main/Audio/AI-based.md#-- ) \ [Enhancers page](https://github.com/FORARTfe/HyMPS/blob/main/Audio/AI-Enhancing.md#---...

MarcoRavich

model uses SubPixel1D, model uses with capital D letter.

ValdemarQ

in model, there is another type: x1 = self.bottle**b**eck(down_outs[-1]) should be: x1 = self.bottle**n**eck(down_outs[-1])

ValdemarQ

I noticed you use padding for convolutions as: `padding=kernel/2 ` But it seems that your kernel size are not even numbers: `n_filtersizes = [65, 33, 17, 9, 9, 9, 9,...

ValdemarQ

In model.py self.bottleneck = Bottleneck(in_channels, _**n_filter**_[-1], n_filtersizes[-1]) Should be replace: self.bottleneck = Bottleneck(in_channels, **_n_filters_**[-1], n_filtersizes[-1])

ValdemarQ