pip install masked_prosody_model==0.1.0

torch and torchaudio need to be installed as well.

from masked_prosody_model import MaskedProsodyModel
model = MaskedProsodyModel.from_pretrained("cdminix/masked_prosody_model")
representation = model.process("some_audio.wav", layer=7) # layer between 0 and 15, 7 was used in the paper