Steven Atkinson

[NeuralAmpModeler.RPP]() References audio files that aren't part of this project. This gets me thinking that the project should include the following: * An audio track to play * At least...

Make a documentation page for this. It'll help.

Improve MRSTFT loss on MPS

2

Prerequisite to #436. Try to make MRSTFT at least run partially on MPS to minimize the speed hit.

**Describe the bug** Python crashes on the GUI trainer on Ctrl+C. Error message is ``` /Users/steve/opt/anaconda3/envs/nam/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at...

What if `GetUI()` returns null? _Originally posted by @sdatkinson in https://github.com/sdatkinson/NeuralAmpModelerPlugin/pull/494#discussion_r1769635237_

Sort of a go-back on #475 but let's leave the native sample rate visible on the details/settings page :)

I want to give folks a checklist of things to test for when making a PR so that they know that they've thought through everything.

[FEATURE] v3_1_0.wav support

2

Implement stuff to recognize [v3_1_0.wav](https://drive.google.com/file/d/1hdSPQmr-tWQR3mPUk1pV_ak1ODL7J-Xz/view?usp=drive_link) better.

[BREAKING] Don't require pre-silence in data

1

https://github.com/sdatkinson/neural-amp-modeler/blob/50df283d619f6940450a4eb00dcfb063c617b7b6/nam/data.py#L244C9-L244C34 I don't buy my argument because this is what the receptive field (`nx`) is for--the first output that we care about is far enough into the output audio that...