Chameleon is a guitar plugin/standalone app using neural networks to create three distinct sounds from a vintage style amp head. The core sound comes from a neural net inference engine which allows the plugin to disguise itself as a high end tube amplifier. Advanced machine learning was used to capture three distinct sounds, named Red (high gain), Gold (crunchy), and Green (clean). In the same way a real amp head is used with a cabinet and other effects, this plugin is intended to be used in the signal chain along with IR's (cab sim), reverb, and any number of guitar effects.
Chameleon is free and open source on Github for anyone interested in audio DSP with machine learning and neural networks. The capture technique used here is capable of reproducing the dynamic response of real amps and pedals to near perfection.
***For best results, use with 44.1kHz samplerate, which is the optimum samplerate of these particular neural net models.***.
Check out the source code on GitHub.
Read the tech article published on Towards Data Science.
Visit the website for more from GuitarML.
Sem comentários:
Enviar um comentário