How to build a voice assistant with open source Rasa and Mozilla tools

In this blog I got it working till the jumping ball. Once I add the and credentials.yml file, i get exception error: Exception: Failed to find input channel class for ‘socketio_connector.SocketIOInput’. Unknown input channel. Check your credentials configuration to make sure the mentioned channel is not misspelled. If you are creating your own channel, make sure it is a proper name of a class in a module. Can you please advice what is the error and how to resolve this.


I got that error solved but after running this command **rasa run --enable-api -p 5005** i am stuck at this error TypeError: CreateModel() takes at most 2 arguments (5 given)

Here is the screenshot of the error. @erohmensing @Juste

Hi, I’m facing the same issue. If you find the solution please let me know.

ok sure

That is because you are using different version of Deepspeech. In version 0.51, class Model used 5 arguments, in version 0.61 Model uses 2 arguments. Yesterday they introduced version 0.7, in which Model uses just 1 argument. So, you should either install Deepspeech version 0.51, or check documentation in order to make it work with newer versions. Cheers


I followed this tutorial, when running rasa run actions --actions actions.actions the following error appears, does anyone know how to solve it?

Hi, how is your experience with latency in this setup? Sorry for jumping in, on facing considerable latency issues with this setup. Running locally atm but still. Any tips would mean the world. Cheers

@Abbas ICapture

in credentials.yml file, add a line as per this snippet. you will not get any error related socket.

@Neary-li you should run cmd as administrator and run command then It might work.