diff --git a/android/en/android-20201215-jarbas.tar.gz b/android/en/android-20201215-jarbas.tar.gz new file mode 100644 index 0000000..b01e717 Binary files /dev/null and b/android/en/android-20201215-jarbas.tar.gz differ diff --git a/android/en/models/README.md b/android/en/models/README.md new file mode 100644 index 0000000..8914e9f --- /dev/null +++ b/android/en/models/README.md @@ -0,0 +1,35 @@ +# Android models + + +### EN +#### android-en-0.3-20201215-jarbas.tar.gz +Trained using a personal dataset, for not wake-word the google-commands +dataset, false_activations-20201215.tar.gz, bg_noise-20201215.tar.gz and +noises-20190814-elt.tar.gz were used + +Training data contained several speakers from various countries and genders, +with about 3 samples per speaker, microphone quality and pronounciation varied +a lot per speaker + +Added to this 64 samples of my own voice collected with mycroft-core during +testing of the initial model available at android-20201215-jarbas.tar.gz + + +=== TrainData === +- wake_words=114 +- not_wake_words=14444 +- test_wake_words=38 +- test_not_wake_words=14496 + + +=== Test set results === +- 14513 out of 14533 +- 99.86% +- 0.07% false positives +- 26.32% false negatives + + +- False Positives: 10 +- True Negatives: 14485 +- False Negatives: 10 +- True Positives: 28 diff --git a/android/en/models/android-en-0.3-20201215-jarbas.tar.gz b/android/en/models/android-en-0.3-20201215-jarbas.tar.gz new file mode 100644 index 0000000..790dd7d Binary files /dev/null and b/android/en/models/android-en-0.3-20201215-jarbas.tar.gz differ diff --git a/licenses/license-20201215-jarbas.txt b/licenses/license-20201215-jarbas.txt new file mode 100644 index 0000000..ba3719e --- /dev/null +++ b/licenses/license-20201215-jarbas.txt @@ -0,0 +1,9 @@ +I, JarbasAi, hereby agree to waive all claim of copyright (economic and moral) in all content contributed by me, the user, and immediately place any and all contributions by me into the public domain, unless otherwise noted. +I grant anyone the right to use my work for any purpose, without any conditions, to be changed or destroyed in any manner whatsoever without any attribution or notification. +No warranties are given. + +Files released into public domain: +not-wake-words/noises/bg_noise-20201215-jarbas.tar.gz +not-wake-words/noises/false_activations-20201215-jarbas.tar.gz +android/en/models/android-en-0.3-20201215-jarbas.tar.gz +android/en/android-20201215-jarbas.tar.gz diff --git a/not-wake-words/noises/bg_noise-20201215-jarbas-readme.md b/not-wake-words/noises/bg_noise-20201215-jarbas-readme.md new file mode 100644 index 0000000..15b1c1d --- /dev/null +++ b/not-wake-words/noises/bg_noise-20201215-jarbas-readme.md @@ -0,0 +1,3 @@ +These samples are "silence" cropped from in between wake word recordings, +meaning a long recording contained several wake word samples and this is +the silence in between \ No newline at end of file diff --git a/not-wake-words/noises/bg_noise-20201215-jarbas.tar.gz b/not-wake-words/noises/bg_noise-20201215-jarbas.tar.gz new file mode 100644 index 0000000..72c6d08 Binary files /dev/null and b/not-wake-words/noises/bg_noise-20201215-jarbas.tar.gz differ diff --git a/not-wake-words/noises/false_activations-20201215-jarbas-readme.md b/not-wake-words/noises/false_activations-20201215-jarbas-readme.md new file mode 100644 index 0000000..e4d4bba --- /dev/null +++ b/not-wake-words/noises/false_activations-20201215-jarbas-readme.md @@ -0,0 +1,7 @@ +These samples are false activations recorded by mycroft-core with the +"record_wake_words" flag set to True + +In northern portugal it's common to say "ó XXX" instead of "hey XXX", a +model i was training learned to always trigger on the "ó", many of these +samples reflect that and should be helpful for this kind of wake word. +Other samples will contain random noises and potentially some dialog from TV \ No newline at end of file diff --git a/not-wake-words/noises/false_activations-20201215-jarbas.tar.gz b/not-wake-words/noises/false_activations-20201215-jarbas.tar.gz new file mode 100644 index 0000000..9cd65cf Binary files /dev/null and b/not-wake-words/noises/false_activations-20201215-jarbas.tar.gz differ