!!! Bugs
wakeword is only a few times spoken and bad detection sorted out. you could not do that through speech. i have thought about it and make a skill.
I love your idea keep up the good work!
You absolutely need to add a requrements.txt to your skill so that mycroft can automatically install dependencies on âmsm installâ.
I just needed to add wget so no big deal⌠Itâs working out of the box for meâŚ
I would try to let precise calculate asyncâŚ
it took a really long time, and didnât warn me.
(without looking at the logs I would have thought of major failure and most likey hit a kill switch, since I am not very patient)
than i get the following errors:
not-wake-word/en-short/notcomputer-en-1ea1c5bc-d2fa-11e9-aa7a-54a050546b1f.wavâ : Signed 16 bit Little Endian, Rate 16000 Hz, Mono
/bin/sh: 1: /home/cola/.mycroft/skills/WakeWord/precise/.venv/bin/python: not found
14:05:31.240 - WakeWord - INFO - precise file computer not found
14:05:34.262 - WakeWord - INFO - precise: check for end calculation
Normally the installation should be done automatically. I think I have to think of something to make it transparent. have fun while testing. I have already fixed some bugs in the last few days. Installation may take up to 30 minutes. which os do you use?
I am using KDE Neon. It worked up to the end of the trainingâŚ
Now itâs stuck in an endless " 14:44:16.238 - WakeWord - INFO - precise: check for end calculation" loop.
Great initiative! And thnx for creating this, I do have a few questions if you donât mind:
After the 12 times you have to say the wake-word it asks something like ânow with over influencing wordsâ, I canât quite catch what is said, what are you supposed to say then? And when do you stop?
How will I know if âcalculationsâ are finished in the end? (and the wake-word is ready?)
How do I change to the newly created wake-word?
*Edit: Btw If I ask âhey Mycroftâ if I can call her the new Wake-word, then she asks âI already learned that, would you like to discard that?â, no matter what I answer yes or no, it always starts recording againâŚ
not wakeword is an example of âBrittaâ are âPrittaâ or âbriteâ.
the skill should make an output after the final calculation, but it can take a few minutes. You can see the progress in the log. or the installation also takes hours.
if you say âI want to call you {name} nowâ and mycroft found a modell, mycroft will setup this directly"
PS:.if you say yes you will create a new model. if you say new, the model will be added and recalculated.
Ok, it does kindah work (although I saw quite some errorâs/deprecated commands being usedâŚat least thatâs what the system is warning aboutâŚ
Hmm, well anything really is regarded as the answer âyes, discard and do this anewâ, whether it is to say yes, no, new or totally silent⌠this is really confusing⌠how would you change to another wakeword being activated without changing the files associated?
I understand that this is under development, but I can see itâs great potential!! ( I really do like the custom wake-word and see this as one of the strong points of this assistant!)
At the moment after a few tries, it didnât really get any betterâŚin a matter of factâŚit got worse, now it seems that with any level above the normal ânoise-levelâ the new âwake-wordâ is triggeredâŚsadly :-/
Have an option the further perfect the wake-word by saying something like "I would like to add more wake-word samples for ânameâ ", in order to have more than 12 samplesâŚ
It would be nice if there is an option to change what wake-word you want to use (perhaps within the settings) so that you can fallback to another wake-word if the new wake-word you created failsâŚ
that is already set up. you can send your data to community-data (currently you have to put in a fork in your github first). I donât really know what works and what doesnât.
lock on Github doc and at the intent files for all options.
Only when your model is available is set up but I can not check the model for correctness.
Hey Gras64, bear with meâŚIâm a novice at bestâŚ
âif you say âI want to call you {name} nowâ and mycroft found a modell, mycroft will setup this directlyâ
PS:.if you say yes you will create a new model. if you say new, the model will be added and recalculated."
I tried this again, but no matter what I sayâŚeven when Iâm silent it will start with the 12 beeps. This could be a language thing, but I would expect the following when it asks âI already know this {name}, would you like to discard?â:
yes- restart learning, begin from new for {name}âŚ
no- activate the {name} wakeword
I donât understand what you say (itâs probably because of language differences?). Let me explain myself better. What I think (and perhaps Iâm seeing this wrong) is that because the Mycroft-wakeword works so well, we could perhaps use the ânot-wake-wordsâ (and noises) from the Mycroft-wakeword and add only a few ânot-wake-wordsâ for our New-wakeword (or is this already done in this matter?). Iâm asking this, because at the moment my New-wakeword is triggered by âsilenceââŚ
4a) No matter if I try to âredefineâ my New-wakeword, this triggering by âsilenceâ seems to stay/get worseâŚ
Yes, it doesnât matter if it is correct, it would be nice to be able to change the âactiveâ Wake-word *at the moment I have no idea how to delete my New-wakeword and revert back to the Mycroft-wakeword⌠(also see 3)
if you say âtrain wackword {name}â .make start train (ask for new or old model). if you say âI want to call you hey mycroft nowâ mycroft check for model and if not found start training (ask for new or old model).
the 12 wakewords are not checked. that is, once you have silence, the silence is also adopted in the model. precise needs a lot more files to work well.
you can view, check and delete all audiofiles and precice files /.mycroft/skills/wake-word/
without a âcheckâ this function really does more harm than good (see 7)
ok
thnx!
Ok, let me explain why this is reallyâŚI mean really bad. What do you think happens when I say âI want to call you hey Mycroft nowâ and it hears it as; âhey Microâ, âhey Microsoftâ, or even âhey MicroftââŚeven when I copy and pasted the sentence you wrote here⌠it âthoughtâ it was a new wake-word and started again listening for the 12âŚetc.
I really think you made a really awesome skill, offcourse it needs still quite some work, but please change the implementation of the questionsâŚ
*btw I checked the actual sound-recordings, and itâs quite a messâŚthe âbeepâ seems also recorded and I think perhaps it would be good to disable the active wake-word, so she will not talk/interfere while recordingâŚ
I worked with delays in part, so I will strive for a different solution. Which hardware and which audio management do you use?
As for hey mycroft and mycrosoft, could that be due to your STT? For me, STT works very well.
I have a Pi 4b, with a sony ps3 eyecam, and normal 3.5 jack outâŚ
I donât know about STT (speech to text?). I do know that even if I typed the command you wrote here in the console in putty (mycroft-cli-client) it didnât even work. And well by saying things you get a more error-prone result. In my humble opinion these commands should be separated:
-to create a new wake-word
-to add extra wake-word voice samples
-to add extra not-wake-word voice samples
-to change the active wake-word
-and perhaps something for the feedback if the wake-word was heard correctly or not
so no big deal⌠Itâs working out of the box for me⌠
and most likey hit a kill switch, since I am not very patient)