26 commits

Author	SHA1	Message	Date
David Scripka	1ae41de488	Adjusted training config example [skip ci]	2023-10-07 21:32:03 -04:00
David Scripka	ef50fcf1c1	Fixed bugs in auto-training process, removed deprecated arguments [skip ci]	2023-10-07 21:27:43 -04:00
David Scripka	dfdeaa2f8d	Small adjustments to training config file and train.py	2023-10-01 20:18:48 -04:00
dscripka	f3e74cd8c4	Working example of automatic model training complete [skip ci]	2023-09-04 11:15:50 -04:00
dscripka	d7e2626980	Partial draft of automatic model training example notebook, updates to train.py [skip ci]	2023-09-03 22:54:26 -04:00
dscripka	1815ca5478	Added example YML file for training new models	2023-09-03 20:33:44 -04:00
dscripka	6aef18da2c	Updated/added functions to support auto training of new wakeword models, tests not yet passing [skip ci]	2023-08-15 22:06:25 -04:00
dscripka	cdd1e529ab	Adjust args microphone stream example, util function bugfix [skip ci]	2023-06-13 21:23:57 -04:00
dscripka	cf2ebc176d	Changed overall prediction behavior to support varying sizes of audio frames/chunks, which leads to efficiency gains on streaming melspectrogram calculations	2023-03-20 21:32:39 -04:00
dscripka	2bcf377431	readme update [skip ci]	2023-03-05 00:38:08 -05:00
dscripka	461d7da628	Added argument to control activation sounds in example script	2023-03-05 00:35:42 -05:00
dscripka	89b63051b6	Typo fixes in documentation [skip ci]	2023-03-04 23:58:12 -05:00
dscripka	9f19d307d8	fixed path issue and updated readme [skip ci]	2023-03-04 23:47:44 -05:00
Bartmoss	59da66890c	Update README.md	2023-02-04 17:13:57 +01:00
Bartmoss	a5fb83143f	finished adding beep and loading one model parameter for capture_activations	2023-02-04 15:34:24 +01:00
Bartmoss	1e93daa4aa	beep on activation WIP	2023-01-29 22:31:45 +01:00
dscripka	1f0ee10efe	Adjusted some example scripts to fix bugs and removed 'plotext' usage as it wasn't functioning right on low-power hardware	2023-01-28 13:58:57 -05:00
dscripka	9d08b95b32	Updated readme's for installation instructions	2023-01-28 11:17:37 -05:00
dscripka	2edd4f547e	Added some scripts and functions to assist with collection false activations	2023-01-22 20:06:37 -05:00
dscripka	81badf5728	Added example script to save audio around an activation to aid in debugging and performance testing, added new data augmentation method using random noise	2023-01-08 13:41:07 -05:00
dscripka	216f0329f4	Added example script for saving model activations to WAV files	2023-01-07 12:28:35 -05:00
dscripka	bc3febc9c1	Final preparation for initial release	2022-12-23 14:51:49 -05:00
dscripka	17586c3d8f	Updated local demo, changes how pre-trained models are loaded	2022-11-21 11:56:43 -05:00
dscripka	2ccb903d61	Small changes/bug fixes, starting refactor in preparation for first release	2022-10-27 21:13:30 -04:00
dscripka	c1466374ba	Changes some filenames, started to work on docs, added a function	2022-10-09 23:45:09 -04:00
dscripka	478fb0f5ae	Added example script for real-time microphone inference	2022-09-28 22:50:34 -04:00