[Azure Batch Speech-to-text] Unable to do Diarization Analysis on Mono wav file

(1) Share

Report

Posted on by televisi

Hi,

I have a mono wav file that I'm trying to do diarization analysis using Transcribe audio files to text from Azure Blob Power Automate template.

Wav file information:

The wav file is an audio recording of two people talking (done by our call center team and customer).

And according to the supported audio format, it is the one that is supported too: here

When I checked the TranscriptionResult, it only shows a single speaker.

The following is the JSON result (extracted and represented using Notepad++ JSON viewer):

Does this mean my wav file is not the correct input?

Thanks!

PS: I selected "Licensing" categories to this post, as there is no other option I can select and it's a mandatory field too...

Categories:

All responses (1)

Answers (0)