andreasjansson / fmsynth

Implicit neural differentiable FM synthesizer

Demo API Examples Versions (af7eb6a7)

Run time and cost

Predictions run on Nvidia A100 (40GB) GPU hardware. Predictions typically complete within 78 seconds. The predict time for this model varies significantly based on the inputs.

Implicit neural differentiable FM synthesizer, implemented during the Neural Audio Synthesis Hackathon 2021.

See the GitHub repo for more details.