Hi guys, I have an interview with two speakers, Amazon Transcribe processed the audio but it outputs an illegible json file, and I need a transcript that separates the two speakers. The preview on amazon transcribe does this perfectly but it only shows the beginning of the transcript
Is there a simple way to convert the json file to something readable? I've tried this but it breaks the text down with time stamps instead of identifying the two different speakers https://yash.info/aws-srt-creator.htm , and I don't need the timestamps, just the diarization which this tool doesn't do
I have literally zero coding knowledge and don't even know how to incorporate any of the github scripts I've found into AWS so I would appreciate recommendations for a simple tool (or alternatively an explanation like I'm five)
It's super frustrating considering Amazon transcribe can clearly output an organized transcript but only offers an option to download a json file
Thank you in advance for the help