Stuck at setup forever

[hedonnn]

On Windows 11, I'm stuck at the sound test.

The app keep saying forever to restart, then I do the setup again (I did it at least 20 times by now), then it says "ok restart" and stays in that loop forever.

I closed Powershell and re-opened it, in Admin, the issue persits.

What can I do?

Also for some reason it's mentioned that API keys are empty?! But I do provide one in the setup (that I've done 20 times).

Server started on http://localhost:3000
API keys are empty, initializing setup screen...
Python Output: [Miles is Downloading wake word model...]

Python Output: [Miles is Wake word models downloaded...]

Python Output: [Miles is Downloading speech recognition models...]

Python Output: [Miles is Base model downloaded successfully...]

Python Output: [Miles is Downloading tiny model...]

Python Output: [Miles is Tiny model downloaded successfully...]

Python Output: [Miles is Ready for speech, try saying 'this is a test']

Python Output: Switching to tiny model due to: Transcription took longer than 3 seconds with the base model.

Python Output: [Miles is You said:  This is a test.]

Python Output: [Miles is Config Complete!]

Config script exited with code 0

[small-cactus]

You need to provide all api keys, if any of them are empty nothing else will work

[hedonnn]

Oh well I couldn't have guessed that, I don't have a Spotify account and don't intend to use any...

[small-cactus]

You don't need a premium account, just a free developer account.

To use the Spotify features you need a premium account, but the app will work without one as long as the API keys are set to something that isn't empty.

You can open the apikeys.py file and replace empty with any random characters for the Spotify values and the app will run without them. If you ask miles to play a song the app will probably crash though.

[hedonnn]

OK now I don't find any apikeys.py file anywhere unfortunately...

EDIT: nevermind I found it it's apikey.py not apikeys.py

I'm trying now.

[hedonnn]

It's stuck at "Listening for Miles"

My mic is working, I say "Miles" "hey miles" "hi miles", nothing happens..

`PS C:\Miles-env\M.I.L.E.S\Miles-V2> npm start

[email protected] start
electron .

Server started on http://localhost:3000
API keys are set, starting server and backend...
Server is already running on port 3000
Python Error: C:\Miles-env\M.I.L.E.S\Miles-V2\main.py:1: DeprecationWarning: 'cgi' is deprecated and slated for removal in Python 3.13
from cgi import print_directory

Python Output: Tool list JSON has been saved to C:\Miles-env\M.I.L.E.S\Miles-V2\plugin_tool_list.json

Python Output: Listening for 'Miles'...
`

[small-cactus]

Adjust the threshold in main.py,They are located at Line 1071 and line 1084. Adjust the correct one for your platform.

[hedonnn]

OK I set it up at 0.0001 and I went pass by "Listening to Miles" it's now stuck at "Listening for prompt" it doesn't seems to listen at all, nothing happens when I talk to it.

[small-cactus]

You either have a very loud room, a noisy mic, or the mic isn't working for Miles at all

[hedonnn]

I don't think it would pass the "listening for "Miles" if it wasn't working.
My room is very very very quiet. Maybe the software doesn't recognize my mic anymore past the first "Listening for Miles"?

[small-cactus]

My wake word detection doesn't use transcribed words to hear you, it uses a neural network to predict when you say the word, so it might go off, and then the actual transcription might not be able to hear you if there's too much background noise, it'll never stop listening because it thinks you're still talking