sin2pi

There is so much wrong here that I'm surprised to see it even discussed.

I'm tinkering with relative positional encoding by trying to integrate acoustic features directly into it.

More specifically, I'm trying to use pitch (F0) to dynamically adjust the theta parameter in rotary positional embeddings, so the frequency of the positional encoding reflects the underlying pitch contour of the speech and instead of using a fixed unit circle (radius=1.0) for complex rotations, I'm trying to work out how to use variable radii derived from the pitch. The idea is to create acoustically-weighted positional encodings, where the position reflects the acoustic salience in the original audio. https://github.com/sine2pi/asr_model

I searched for awhile on how to ask a question about asking a question on HN and I stumbled upon a thread that said to do exactly what I did and I just went for it. Thank you for clearing that up for me.