MMM-voice

AxLed

@AxLed https://cmusphinx.github.io/wiki/faq/#q-which-languages-are-supported

@strawberrxyy 3.141

I tried to change the language to german / german voice recognition with some informations from here:
https://mycroft.ai/documentation/language-support/german/
but my skills a not good enough to get it working.

3 more questions:
Is there a command for commandline to test Pocketsphinx and its components, so maybe i can find out where i went in the wrong direction.

Do i need for changing the language model only have to download certain files and bring them in the right structure or do i have to compile something afterwards?

Where could i change the path to other language models in MMM-voice, i only found links to the .lm an .dic file but not to the .../model/en-us/ structure.

AxLED

strawberry 3.141

@AxLed

pocketsphinx_continuous
You need to look for instructions where you downloaded those files
you can specify the language model with the option -hmm in the node dependencie pocketsphinx-continuous-node

maxbachmann

In case you get it running in German can you share it?
could really use this as well :)

Max

strawberry 3.141

@maxbachmann even if he’s able to get german running are the commands and supported modules only working with english, to make this possible there is a big effort necessary, that I cannot put in anymore

prs are highly welcome for this, but make sure to discuss possible implementations upfront, to avoid getting the pull request rejected

maxbachmann

oh I mean that in case he manages it he could share it :)
I will probably go with the english voice control for now because there are already many working modules out there

tbbear

@maxbachmann
Hi, the modules get signals to act and it realy doesnt matter in with language u use the voice.

By the way i am also interested if u get it working in german

maxbachmann

yeah but you still need to train it for the language

djsunrise19

@strawberry-3.141 said in MMM-voice:

We could get Around the issue of @witschi87 but we dont know yet what the problem actually is. When he starts his mirror with DISPLAY=:0 nohup npm start & it works, with pm2 start mm not, but i have seen a couple using it with pm2 already

@iMAGiC sry I my Time is pretty Limited due to my Bachelor thesis, but i will have a look if i can adjust the Existent Music player to Voice commands easily

@strawberry-3.141 Any news here? I have the same problem. It works with pm2 restart mm but not after a reboot. Error 1.

sispheor

Guys,
If you want to try a multiple languages and self hosted module you can take a look here: https://forum.magicmirror.builders/topic/6615/kalliope-assistant-mm

This module allow you to bind MM to Kalliope assistant.

Demo:
https://www.youtube.com/watch?v=QHwctPbJ2ZY

dogfeet

hi guys, i’m a little over my head here, really not familiar with coding very much but i’ve got voice working and been able to tweak a few things.

what i want to do is probably very easy but i just can’t get it to work. i want to have mmm-voice control the default compliments module such that compliments begins hidden by default and i can say “how do i look” and the mirror will show the compliments module for 10 seconds then hide it again.

i could change the compliments to have appropriate responses and then when the user says “how do i look” the mirror will appear to answer them.

i was thinking of setting “HOW DO” as the mode command to control the compliments module and then “I LOOK” could be the command within that mode to show a compliment for 10 seconds.

what do you think? is this a simple task?