Help decoding downloaded transcript

Question

I used Amazon Transcribe real time transcription service, recording audio live. When I downloaded the transcript, it saved as a JSON file comprised of 13,000 pages of text. Does anyone know how I can  get the simple text output from the transcription vs. all the raw source code output? Or is there a way to convert the JSON file I have into an output that can be read more easily?

Answer

Hi, the JSON file you received from Amazon Transcribe contains a lot of metadata and additional information along with the transcribed text. To extract just the transcribed text from the JSON file, you can use a programming language like Python and its built-in JSON library.
If you want to convert your JSON output into a turn-by-turn transcript in Word format, see this: https://github.com/aws-samples/amazon-transcribe-output-word-document

Help decoding downloaded transcript

Relevanter Inhalt