2

When i am trying to do a speech to text transcribe of a live phone call using web socket.

Already included 

const Speech = require('@google-cloud/speech').v1p1beta1;

const speech = new Speech.SpeechClient();

With following config.

encoding: 'LINEAR16',
sampleRateHertz: 8000,
languageCode: 'en-US',
useEnhanced: true,
enableSpeakerDiarization: true,
diarizationSpeakerCount: 2,
enableWordConfidence: true,
model: `phone_call`,

I am getting following response

{
  "results": [
    {
      "alternatives": [
        {
          "words": [],
          "transcript": " what I'm trying to do is",
          "confidence": 0.778500497341156
        }
      ],
      "isFinal": true,
      "stability": 0
    }
  ],
  "error": null,
  "speechEventType": "SPEECH_EVENT_UNSPECIFIED"
}

Do you guys know why i am not getting speaker diarization in the response from the google cloud for the above config?

Binu Mathew
  • 55
  • 1
  • 10
  • I think we are going to need more context. While I dislike posts with lots of code, perhaps post your code as an attachment or as a link. We are likely going to want to see the whole context of how you are processing the audio. Also a written example of what the audio contains and what you anticipate the output to be. – Kolban Jun 09 '19 at 15:52

0 Answers0