neural-amp-modeler
neural-amp-modeler copied to clipboard
sdatkinson
Neural network emulator for guitar amplifiers.
Warnings are good! Currently they are checked as they are trained, which can result in a problem in the middle of the night. Not good!
How it's split, how there are repeats, how you need to be silent before the start of a section. With pictures.
Hello nice people! ### Context Lately I've been running some tests on the NAM models with the goal of improving the training procedure, optimizing the CPU consumption of the generated...
Option to incorporate a convolutional layer in front of LSTM models. Helps w/ sensitivity to delay, and generally improves training.
It can save a lot of storage space and Google Colab's upload speed is slow so this would also help there.
There's a plot that's supposed to show, but it doesn't. e.g. On Colab (lower white space is Tensorboard, not the desired plot): Observed on local as well. Solve by gathering...
In order to upgrade old .nam models with loudness metadata, we need to be able to instantiate them as PyTorch models. so that we can run the method on them....
Currently on sites like tone hunt captures are organised in groups for example 6 captures of different control settings for a single amp, but there is no metadata standard for...
I think this is a general topic, probably spanning multiple future & existing issues. Also, it's probably something for the medium-to-long term future :D (Some) related pre-existing issues: https://github.com/sdatkinson/neural-amp-modeler/issues/176 https://github.com/sdatkinson/neural-amp-modeler/issues/140...
It would be great to have a meta data field for the dBu level the reamp device is calibrated for. Currently, because everyone is using a wide variety of different...
Metadata
Owner
Metadata
Neural network emulator for guitar amplifiers.