0

[Edited]

So, I used Amazon Transcribe (https://aws.amazon.com/transcribe), by clicking create jobs

Then, I did a job setting thing (in Amazon Transcribe > Transcription jobs > Create transcription job).

Used a Japanese mp3 file and set Speaker identification to Speaker identification and Alternative results to Enabled.

Finally when I see the result, LENCE] sometimes appears in it.

What does it mean?

I could not find any explanation for this in AWS website.

Thanks

John Rotenstein
  • 241,921
  • 22
  • 380
  • 470
gota
  • 9
  • 5
  • Can you possibly edit your question and provide more information so that we can try to reproduce this situation? Or at least tell us more about what you are doing (which commands on what data) and where you are seeing this message? – John Rotenstein Nov 25 '19 at 05:34
  • Cheers, I edited my question. I hope it got more informative. – gota Nov 26 '19 at 06:51

1 Answers1

0

It looks a little bit like the word SILENCE, which might indicate a gap in the conversation.

From Channel Identification - Amazon Transcribe:

Speakers' utterances are ordered by their start time. An utterance is a unit of speech on the audio channel that is typically separated from other utterances by silence. If an utterance on one channel overlaps one on another channel, Amazon Transcribe orders them in the transcription by their start times. Utterances that overlap in the input audio don't overlap in the transcription output.

John Rotenstein
  • 241,921
  • 22
  • 380
  • 470