Hi, Currently in GuitarMidi-lv2 I have a neural net that is trained on data obtained in frame buffers of 256 samples at 48khz. Thats why the plugin only operates at those parameters.
To make the plugin operate at any framebuffer without having to retrain the model for different buffersizes the idea is just to buffer the audio in an internal 256 sample buffer, should the host buffersize be smaller than 256, or run the plugin n times should the host buffersize be n*256, so that problem is solved. The question is how should I handle samplerates other than 48khz? I could implement simple interpolation schemes for samplerates lower than 48khz and subsampling for higher samplerates. What are the potholes? Are there libraries out there that can do this in real time in the audio thread? I want to resample to 48khz, again so I can run the same neural net regardless if the host samplerate. Thanks, Gerald
