awslabs / amazon-transcribe-streaming-sdk

The Amazon Transcribe Streaming SDK is an async Python SDK for converting audio into text via Amazon Transcribe.
Apache License 2.0
142 stars 37 forks source link

AWS transcribe speaker identification #42

Open haldernayan opened 3 years ago

haldernayan commented 3 years ago

1) online live streaming in AWS Console webpage :

I noticed there is a checkbox in AWS transcribe console, it is mentioned that speaker1/speaker2 will be displayed in aws UI console. But how to test that over microphone.

In offline ASR, it is easy to test, just send multiple speakers single audio file to aws transcribe , it will recognise speakers.

but in online streaming how to test 2 speakers.

in online streaming for myself only( 1 speaker case) it is working fine.

to test 2 speakers, does my friend ( acted as 2nd speaker) login in the same aws user account. but how microphone will concurrently send both speakers sound to live streaming to identify speaker1/speaker2.

2) does simple_mic.py can recognise 2 speakers. if yes how to test.

3) does simple_file.py can recognise 2 speakers.