By using AWS re:Post, you agree to the Terms of Use
AWS re:Postre:Post

Speech to Text for one speaker

0

Hello, I have an audio file which contains only 1 speaker recording. When I use the console, I choose Speaker Identification. When the task is completed, I am seeing 2 speaker label on json file. I cant specify speaker number below 2.(Rule : min:2 and max:10). How can I produce only 1 speaker output for my audio file.

Best Regards.

Topics
Machine Learning & AI
Tags
Amazon Transcribe
Language
English
basictechs
asked 2 years ago165 views
2 Answers
0

If you only have one speaker then there is no need for speaker identification? Keep the audio identification option disabled

cloud-commander
answered 2 years ago
0

Sorry I forgot the mention that sometimes there would be recordings that will include 2 speakers.

basictechs
answered 2 years ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Guidelines for Answering Questions

Relevant content