Downloads · 30 days
0
masked_prosody_model
cdminix/masked_prosody_model
masked_prosody_model is a machine learning model from cdminix. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-4.0.
torch and torchaudio need to be installed as well.
Access
Public
Updated Oct 31, 2024
Repo size
56.2 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin56.2 MB · 100%
At a glance
- License
- cc-by-4.0
- Access
- Public
- Created
- Oct 17, 2023
- Updated
- Oct 31, 2024
- SHA
- b8230cf6
Spaces
Model card
From the Hugging Face model README
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.
- License
- cc-by-4.0
- Created
- Oct 17, 2023
- Updated
- Oct 31, 2024