96
91%
master: 91%

Ran 16 Jul 2019 07:26PM UTC

Jobs 1

Files 14

Run time 2s

Badge

Embed ▾

pending completion

Build # 96

Build Type

push

circleci

Committed by Brent M. Spell

Commit Message

add support for autoregressive detectors

These changes introduce a new tensorflow "encode" model in the
wakeword trigger, which allows us to implement autoregressive models
for wakeword detection (like rnns and attention). Doing this
efficiently requires running each frame through the encoder and then
aggregating these frames for attention/classification, in order to
avoid redundant calls to the encoder. These models also provide the
ability to detect whole phrases with long-range frame dependencies,
so we no longer need manual phrasing or smoothing logic and buffers.
For an example model, see https://arxiv.org/abs/1803.10916

Run Details

853 of 936 relevant lines covered (91.13%)

0.91 hits per line

Jobs

ID	Job ID	Ran	Files	Coverage
1	96.1	16 Jul 2019 07:26PM UTC	0	91.13

Source Files on build 96

Detailed source file information is not available for this build.

pylon / spokestack-android / 96
91%
master: 91%

README BADGES
x

Markdown

Textile

RDoc

HTML

Rst

Jobs

Source Files on build 96

pylon / spokestack-android / 96 91% master: 91%

README BADGES x

Markdown

Textile

RDoc

HTML

Rst

Jobs

Source Files on build 96

pylon / spokestack-android / 96
91%
master: 91%

README BADGES
x