PyPI page
Home page
Author:
Marek Sviderski
License:
MIT
Summary:
Deep acoustic feature streams (SSL embeddings, vision, emotion) for acoustic phenotyping
Latest version:
0.1.1
Required dependencies:
huggingface-hub
|
joblib
|
librosa
|
numpy
|
pandas
|
scikit-learn
|
scipy
Optional dependencies:
build
|
pytest
|
ruff
|
torch
|
torchaudio
|
torchvision
|
transformers
Downloads last day:
3
Downloads last week:
19
Downloads last month:
252
7-day smoothing