If a person wanted to transcribe sheet music from recorded audio, do you know which library and features would be the best starting point?

For MIDI:

https://github.com/Music-and-Culture-Technology-Lab/omnizart and https://basicpitch.spotify.com/

They work better if you apply some source separation before (e.g, https://github.com/sigsep/open-unmix-pytorch, https://github.com/facebookresearch/demucs, or https://mvsep.com)

Still, I think the best results are from proprietary models (specifically https://www.ableton.com/en/manual/converting-audio-to-midi/ and https://www.celemony.com/en/melodyne/what-is-melodyne)

I have had mixed luck with this model, which is supposedly state-of-the-art: https://github.com/magenta/mt3

What kind of music are you trying to transcribe?

Feel free to email me.

Start with source separation using demucs

Try our newish music scanning feature at Soundslice:

https://www.soundslice.com/sheet-music-scanner/

Check out librosa as well