It would help if there was a node for:
Aws Transcribe, to create a job and specify the output format.
My use case:
IU am aiming to transcribe podcasts, however, the default output format of an AWS transcription is massive, complicated, and while parsable, not easily so.
The simplification option in the “get transcription” is helpful, however, it destroys the speaker diarisation, and returns the text without any speaker identification whatsoever.
Any resources to support this?
Adding “output format” → vtt or srt to the “create transcription job” node options would enable a much smaller, much more useful output, than the “simplify” option in the “get transcription” fuction.
Are you willing to work on this?
Yes. It’s fairly straightforward, however, I’m not sure how one would write a test for this: I’m a rubyist, and javascript is not my jam.
Thank you!