How is Audio Identification transcription text created from JSON?

I am not familiar with JSON files. For a single speaker, I have been editing the JSON in Word, no problem as the full transcription text is easily extracted. Now for 2 speakers, I would like to extract the Audio Identification transcription text as shown in the 5000 character sample text where the speaker is identified. How do I create the Audio Identification transcription text for the full transcription as shown in the sample, from the JSON file? Thanks.

주제

기계 학습 및 AI

태그

아마존 Transcribe

언어

English

alexim

질문됨 5년 전1370회 조회

3개 답변

최신
최다 투표
가장 많은 댓글

이 답변이 도움이 되었나요?커뮤니티가 여러분의 지식을 활용할 수 있도록 정답을 찬성하세요.

수락된 답변

Hi,
I would recommend using or modifying the aws-transcribe-transcript python script found in the link below. This script will parse the json that contains multiple speakers into a more readable format.
Link: https://github.com/trhr/aws-transcribe-transcript
Hope this helps!
-randy

RandyTakeshita

답변함 5년 전

전문가

Giovanni Lauria

검토됨 한 달 전

threadgillcom
일 년 전
Hi Randy (or anyone with insight on producing a Speaker Partioned/Diarized arsOutput.json file, so the audio transcription can be easier to read),

Thank you for the link (https://github.com/trhr/aws-transcribe-transcript).

Unlike Alexim, I wasn't able to complete the steps (either Regular or S3).

I documented the steps I took, and posted them here: http://threadgill.com/translation.3.html

Any suggestions on how to configure this would be very much appreciated!

Fantastic!!! It worked perfectly. Randy, thank you so much.

alexim

답변함 5년 전

Hi Randy,
Thank you for the link.
Unlike Alexim, I wasn't able to complete the steps (either Regular or S3).
I documented the steps I took, and posted them here: http://threadgill.com/translation.3.html
Any suggestions on how to configure this would be very much appreciated!

threadgillcom

답변함 일 년 전

How is Audio Identification transcription text created from JSON?

관련 콘텐츠