EnCodecMAE: Leveraging neural codecs for universal audio representation learning
Paper
•
2309.07391
•
Published
•
2
Model description
This is EnCodecMAE, an audio feature extractor pretrained with masked language modelling to predict discrete targets generated by EnCodec, a neural audio codec. For more details about the architecture and pretraining procedure, read the paper.
Usage
1) Clone the EnCodecMAE library:
git clone https://github.com/habla-liaa/encodecmae.git
2) Install it:
cd encodecmae
pip install -e .
3) Extract embeddings in Python:
from encodecmae import load_model
model = load_model('large', device='cuda:0')
features = model.extract_features_from_file('gsc/bed/00176480_nohash_0.wav')
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support