Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

be sure to retrain after enable voice-controller #28

Open
kgiori opened this issue Jun 27, 2019 · 0 comments
Open

be sure to retrain after enable voice-controller #28

kgiori opened this issue Jun 27, 2019 · 0 comments

Comments

@kgiori
Copy link

kgiori commented Jun 27, 2019

I had updated to a version 1.0 voice-controller add-on on a 0.8.1 gateway that had the previous voice-controller version. When I plugged the speaker/mic back into it (had been detached), I disabled/enabled the voice-controller. Note to self -- because packages are uninstalled and re-installed for this process, you have to go have coffee or something while waiting (takes a long time on a little RPi.) After updating the config to "hey snips" and waiting some more, then the wake word was being detected, but it failed on a simple command, "turn on the balcony" (a light). I suspect the problem is that after reconfig/retrain/reinstall/restart, somehow the controller didn't "start up" with a known set of thing names in its language model (LM). After I had deleted a thing from my UI, I saw that the voice-controller had done a "retrain" event (saw in log). When I tried a voice command again, it recognized all my thing names. :) So I think that after every "configure" or "enable" of the voice-controller, we should make sure to also run the "retrain" process to make sure the LM is up to date.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant