ibm / watson-speech-translator Goto Github PK

I would like to use the audio stream which is received over the Websocket as input to the SpeechToText service instead of input from the microphone.

Is that possible and is there any example of how to do that?

Thank you in advance.

I followed all the steps with no errors in the process. When I click on the app url, the page loads but it gets stuck where the speech recognition model ha to load the models supported by the speech to text service. I checked the speech to text service's activity feed and it says "an instance of the app crashed: APP/PROC/WEB: Exited with status 137 (out of memory)"
I stopped and restarted the Cloud Foundry app but to the same result. The app's instance seems to be using the entire 256 Mb of memory allocated.
Why does is generate the "out of memory" error? How can this issue be solved?

Thank you