pip install masked_prosody_model
pip install git+https://github.com/minixc/srmrpy

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_audio("some_audio.wav", layer=7) # layer between 0 and 15, 7 was used in the paper

This model was trained using Cloud TPUs supplied by Google’s TPU Research Cloud (TRC). I thank them for their support.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Space using cdminix/masked_prosody_model 1