Segmentation fault rasa train on enabling Intentless Policy

Rasa Pro 3.7 still supports NLU functionality, so the examples in the documentation (which I’m sure you already know about) are a good starting point.

Thank you, will continue with NLU style for reminders.

Removed post as I solved issue

I’m glad you fixed it!

I generally encourage people to retain problems and solutions in the forums, so that later developers who encounter the same problem can learn from the difficulties we face. But I respect your wish to manage the words you share with the public.

I really like to share all problems and especially in the entire new journey that I am on,it is valauble to share But this time it was issue with GCP firewall hence I considered it is outofscope here. But will consider sharing. Thanks, Geeta

I’m building a multilingual voice bot with CALM using a single model and a language translation service, and it’s slow. Is a multi-model architecture generally better for performance in this scenario or are there any alternatives? Here is brief detail of my flow

  1. STT module processes the speech.
  2. Take the output of the STT module (text) and send it to the REST channel of your Rasa server.
  3. Use Translation service to translate to user language.
  4. Take the REST response (text) and send it to the TTS module. And time taken for each is as below Conversion took -1(STT) -->: 3.45 seconds

Conversion took -2(Rasa Response) -->: 24.54 seconds response_content → Warm greetings from MitramCares! I’m your friendly helper. How can I make things easier for you today?

Conversion took -3 (Translation)–>: 0.76 seconds

Conversion took -4(TTS) -->: 0.99 seconds

How can I reduce lag in my Rasa API responses? Would an multi model be a suitable solution for overall speed improvement?

But On GCP it takes lesser time but still Rasa server repsonse takes 5 to 6 seconds for simple custom actions