Number of Hotwords and Sensitivity does not match when using jarvis.umdl

[BarryAlle]

Describe the bug:

Hi,Shiva, i have a problem about custom wakeword.When i add a Path of my model wakeworld in config.yaml,its return this:
ERROR:__main__:number of hotwords in decoder_model (4) and sensitivity (3) does not match
Traceback (most recent call last):
  File "/home/pi/GassistPi/src/main.py", line 560, in <module>
    Myassistant().main()
  File "/home/pi/GassistPi/src/main.py", line 153, in __init__
    self.detector = snowboydecoder.HotwordDetector(models, sensitivity=self.sensitivity)
  File "/home/pi/GassistPi/src/snowboydecoder.py", line 100, in __init__
    "(%d) does not match" % (self.num_hotwords, len(sensitivity))
AssertionError: number of hotwords in decoder_model (4) and sensitivity (3) does not match

Please help me.

Did you go through or search the issues section to check if your issue was already discussed (either currently open issues or closed issues).

Yes/No

2. Is the issue related to assistant installation ?

Yes/No

If answer to question 2 is Yes, then paste the contents of the terminal below.

If answer to question 2 is No, then proceed further.

3. Does the assistant service start normally?

Yes/No

4. Is the assistant service restarting automatically?

Yes/No

If answer to question 4 is Yes, then paste the contents of the terminal below.

If answer to question 4 is No, then proceed further.

Manually start the assistant. For guidelines to start the assistant manually refer this

Paste the command below, that crashed the assistant

Paste the contents of the terminal below

Attach the log file. Log file can be found in /tmp directory. Remeber to copy your log file before shutting down or restarting the Pi.

[shivasiddharth]

Can you please attach your config.yaml file?

[BarryAlle]

Config file for declaring custom actions'parameters. The parameters have been listed here in alphabetical order (A-Z).

Custom wakeword On/Off.

To enable custom wakeword, change status to Enabled and restart the assistant.

Custom_wakeword: status: 'Enabled' models:

• '/home/pi/GassistPi/src/resources/alexa.umdl'
• '/home/pi/GassistPi/src/resources/snowboy.umdl'
• '/home/pi/GassistPi/src/resources/jarvis.umdl'

  ESP control declarations. Follow a similar pattern to add your own list.

  ESP: IP: 'xxxxxxxxxxxx' #Enter your ESP's IP here. devicename:

• 'Device 1'
• 'Device 2'
• 'Device 3' deviceid:

This is my config.yaml p/s: Thnks for spending your time to help me

[shivasiddharth]

Right now, the assistant can take in max 2 wakewords. You have given 3.

[BarryAlle]

but i gave it 2 wakewords still not working

[shivasiddharth]

Please post the output of terminal when you use two wakewords.

[BarryAlle]

My Terminal output: ERROR:main:number of hotwords in decoder_model (3) and sensitivity (2) does not match Traceback (most recent call last): File "/home/pi/GassistPi/src/main.py", line 560, in Myassistant().main() File "/home/pi/GassistPi/src/main.py", line 153, in init self.detector = snowboydecoder.HotwordDetector(models, sensitivity=self.sensitivity) File "/home/pi/GassistPi/src/snowboydecoder.py", line 100, in init "(%d) does not match" % (self.num_hotwords, len(sensitivity)) AssertionError: number of hotwords in decoder_model (3) and sensitivity (2) does not match

I think its still the same

[BarryAlle]

Thats only work with alexa and snowboy but the other its not

[shivasiddharth]

There is an issue with the jarvis.umdl hotword. Please refer to this https://github.com/Kitt-AI/snowboy/issues/447 one jarvis.umdl is being taken as two models. If you want to use jarvis.umdl then make the following change in main.py in lines 151 and 152 in main.py

change len(models) to (len(models)+1) this is if you are using jarvis.umdl only.

[BarryAlle]

How about i want to use 2 model of wakeword? I think its much be easy for my family to use

[BarryAlle]

i have train myself a model call friday but is not working when i use 2 model in config.yaml p/s I put every thing back to default

[shivasiddharth]

what are the two models you are using ?

[BarryAlle]

nevermind, now its working perfectly.Thanks for spending your time to help me

[shivasiddharth]

Closing this issue then.