Metadata-Version: 2.1
Name: sonusai
Version: 0.3.13
Summary: Framework for building deep neural network models for sound, speech, and voice AI
Home-page: http://aaware.com
License: GPL-3.0-only
Author: Chris Eddington
Author-email: chris@aaware.com
Maintainer: Chris Eddington
Maintainer-email: chris@aaware.com
Requires-Python: >=3.8,<3.11
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Requires-Dist: PyYAML (>=6.0,<7.0)
Requires-Dist: docopt (>=0.6,<0.7)
Requires-Dist: h5py (>=2.10.0,<2.11.0)
Requires-Dist: keras2onnx (>=1,<2)
Requires-Dist: matplotlib (>=3.5,<4.0)
Requires-Dist: p-tqdm (>=1.3.3,<2.0.0)
Requires-Dist: pyaaware (>=1.3.9,<2.0.0)
Requires-Dist: sh (>=1.14.2,<2.0.0)
Requires-Dist: sklearn (>=0.0,<0.1)
Requires-Dist: sox (>=1,<2)
Requires-Dist: tensorflow (==2.3.1)
Requires-Dist: tqdm (>=4.62,<5.0)
Description-Content-Type: text/x-rst

Sonus AI: Framework for simplified creation of deep NN models for sound, speech, and voice AI

Sonus AI includes functions for pre-processing training and validation data and
creating performance metrics reports for key types of Keras models:
- recurrent, convolutional, or a combination (i.e. RCNNs)
- binary, multiclass single-label, multiclass multi-label, and regresssion
- training with data augmentations:  noise mixing, pitch and time stretch, etc.

Sonus AI python functions are used by:
 - Aaware Inc. sonusai executable:  Easily create train/validation data, run prediction, evaluate model performance
 - Keras model scripts:             User python scripts for keras model creation, training, and prediction. These can use sonusai-specific data but also some general useful utilities for trainining rnn-based models like CRNN's, DSCRNN's, etc. in Keras

