Open adhitht opened 2 years ago
Build from the codebase via NPM, and the wakeword will work. Since the new release isn't out yet(but will be soon) you will have to build it from source. Get Git and Node JS 16, clone the repo in a folder(random) and run the commands listed in the Readme. Then, open the newly-created dist
folder and you might have to check that. Run the installer there(you bult it so you are secure) or check the linux-unpacked
(doubt here but unpacked confirmed) folder and run the Google Assistant executable for Linux. Then, you are good to go.
Teachable machine can be customised to user so recognition will be far more effective. https://teachablemachine.withgoogle.com/
Wow, @Melvin-Abraham this is a good idea, right? Bumblebee currently can't recognise Ok Google or Hey Google, which means you have to release a little(in my case, a lot) sound, but if we try integrating this, it might recognise Hey Google/Ok Google perfectly, right?
Bumblebee currently can't recognize Ok Google or Hey Google,
Sorry for that... It was actually: Bumblebee currently can't recognize Ok Google/Hey Google quickly or in one sentence, ie. Ok Google.
Bumblebee currently can't recognize Ok Google/Hey Google quickly or in one sentence,
Well keyboard shortcut would be better than that.
I tried some other wake words in bumblebee which seem to work much better. Maybe these could be provided as possible wake-word options...
Teachable machine can be customised to user so recognition will be far more effective. https://teachablemachine.withgoogle.com/
Wow, @Melvin-Abraham this is a good idea, right? Bumblebee currently can't recognise Ok Google or Hey Google, which means you have to release a little(in my case, a lot) sound, but if we try integrating this, it might recognise Hey Google/Ok Google perfectly, right?
This would require a ton of voice data from a number of people with different accents and dialects. If it is trained with a small sample group, it would perform worse for other set of people...
So, my plan for now is to keep using bumblebee with extended functionalities for this release. If that doesn't suffice, maybe we can give it a thought
You can download dataset for one person,so it can be stored at a particular location and accessed by the app. So it will work perfectly for one user.
hey, why not keep one audio file for the voice recog(recognition)? We can use the same way Androids ask for Ok Google and Hey Google twice, right? Can that work?
Did not get what you are talking about. Let me clarify, with teachable machine you have to record background voice and a class, as we are intended to make a wake word, we have to repeatedly say something like Ok Google, or Hey Google, (or both together) and it should be minimum 8 samples for class. At last we have to train model and export data, it gives some zip file with almost a few kilobites of data (two json files and a bin file). We could use them to trigger wake word. So the audio samples have to be collected by user and add it in a directory and make g-assist read that. (Same as in the case of tokens and credentials file). It would be awesome if you could implement that.
I am not sure if teachable machine is a perfect candidate for this use-case. If I am not wrong, it is best fit for distinguishing different quality/types of sounds, different timbre, tones, etc. but not fit for a wake-word detection as it could lead to a plethora of false-positives or false-negatives which could possibly trigger the assistant every-so-often if not trained properly. Also, that might require more than 500 to 1000+ (not a calculated guess) samples for both random noise (false triggers would mostly depend on this) and wake-word classes just for a single person for it to even perform properly which would require a lot of training, thus, space and time overhead. That's just my opinion though...
I say copying the Android Google Assistant Voice Detection setup might work. Two Ok Google audio files and two Hey Google Audio files or just go get them from the global Google Account since they are stored on the Google Account.
Is the wake word available for Windows 10 or is it just for Linux.
@Wizards-god It is there for Windows as well
@sumeshir26 But it does not activate when i say Ok Google or Hey Google or Bumblebee So can you tell me what the wake word is.
Did you build it in the first place?
Build what.
the app
Do you know how to build it?
The bumble bee app you mean?
No i dont actually know how to build it
The GAUDC app.
Could you tell me how to build it.
I have the google assistant app
You have to build the entire app. Don't worry, it is easy but will take time.
Ok can you guide me through it
Alright, time for some tech gobbledygook.
cmd
cd Desktop
git clone https://github.com/Melvin-Abraham/Google-Assistant-Unofficial-Desktop-Client.git
(that's why you need Git, to clone the entire code)cd Google-Assistant-Unofficial-Desktop-Client
npm install && npm run dist
(That's why you need Node JS, it downloads NPM with it, which in turn helps you to install dependencies)explorer
dist
folder and then, win-unpacked
.Google-Assistant.exe
file and GAUDC will launch. Note: Make sure your old GAUDC is successfully closed.Can i uninstall node and git after the procedure?
Then, authenticate it(I expect you know how by now) and go to Settings. Locate Ok Google
and toggle it.
Can i uninstall node and git after the procedure?
If you want. However, I suggest that you don't because the compiled version has bugs. After the new release, new bugs+fixes will be released, so don't uninstall it, use it for GAUDC and if you ever need to make a project like it, NPM will help you. Since new bugs are found almost everyday, and fixes are released, you will lose the fix, so you can build it from the code base whenever you find bugs that are already fixed.
Ok thanks for all the help will try and let you know.
:+1:
Why is node installing visual studio?
I thought it was only node.
I think it needs it. You mainly need Git, Node JS, and Visual Studio's build tools(?) and Windows Build Tools.
Oh ok then.
I am unsure on Visual Studio but I know that you need Windows Build Tools.
It is stuck at this page from the past 6 mins.
Could you please tell me why.
Oh no. You have Windows 11. But did you get Node JS?
I got Git but that screen is that of Node JS
Close that. And open Command Prompt or Windows Terminal
Ok
Follow those commands I put above only. It is also in the README
I tried entering cd Desktop in cmd but it says the system cannot find the specified path
type dir
and send me the screenshot. I don't use Windows 11 so idk about the path.
Ok and i see that the desktop folder is in the OneDrive Folder
Okay... Desktop is gone... Type cd Documents
, everything else is the same.
ok will try that
Could you please explain to me from the 10th step. I did not understand
Go to your desktop
Hover at the right side of your taskbar and press the line that appears there
ok
I have downloaded g-assist from snap store version 1.0.0-rc.2. Wake word doesn't seem to work. (I am not sure if it is built for the version) Please clarify. Saw that wake word detection is built using bumble-bee. I have tried bumble-bee from here : https://jaxcore.github.io/bumblebee-hotword/full-example/. I have tried hey_google and ok_google. But bumble-bee doesn't seem to recognise both. (Had 1 recognition with almost 20 tries :disappointed: ). Alexa seems to hear me. It would to be better if you could just provide option to set other wake-words in settings. I would also suggest teachable machine from google as an alternative to bumble-bee. (It works very well.) Hope you could implement that well. Teachable machine can be customised to user so recognition will be far more effective. https://teachablemachine.withgoogle.com/ snowboy is another depreciated software which can be used to have wake-word detection.