Use RASA with ASR (speech recognition)

Rasa Open Source
1

Hi,

I want to integrate an ASR system, using the SpeechRecognition library (SpeechRecognition · PyPI) in my RASA chatbot. It would be best if I could manage to get a JSON file with the message from ASR and then be able to have that text message inputted in RASA, RASA decided what to do and then gives a JSON file with the textual response back. Does anyone know how to do this?

2

Hi @ellav,

I would recommend running Rasa with a REST API for this, you can handle messages with a POST request to /webhooks/rest/webhook, and it will return the output of the bot (e.g. messages, custom actions)

3

Is there a way to do this without the POST request? I have my own connector file running now (I’ll attach it), and we want to just run it when asr receives something (which is dealt with in the zmq server side) and gives back a json file to te get_text() function with the client side of zmq, which extracts the text.

connector.py (3.1 KB)