Speech Recognition with Audio Nodes

KCH Workflows
1

This workflow shows the functionality of the KNIME Audio nodes - Read in audio files - Use speech-to-text services - Extract acoustic features - Visualize in Component Composite View Pleas note: - The CMUSphinx4 speech recognition service does not require any credentials - Bing and IBM Watson require access to the respective services and the corresponding credentials - The CMUSphinx4 SR node supports the use of custom language models. For more information, visit https://cmusphinx.github.io/wiki/tutoriallm/

This is a companion discussion topic for the original entry at https://kni.me/w/k0eCBc2JpVEDNr0N
2

Hello, IBM Watson node doesn’t accept my credentials.
It seems so that username and password are replaced with API key and service URL.
Is there any way for me to fix this in code?

3

Hi @wl4d and welcome to the forum.

Unfortunately the current implementation of the Watson node does not support authentication via API key. We have a ticket open for this (AP-11183) and I will add your feedback as a +1 there. Sorry for the trouble.

1 Like