We receive multiple audio files every day and it will have sensitive information. We need to mask this information but retain rest of the audio.
The way I see it we need to perform below steps first we need to use speech recognition and identify sensitive info (one of our case is credit card info) then we need redact/ mask. we need a workaround on how to redact that info retaining rest of the audio as is. we are okay if we are trimming it or nullifying the frequency factor or replacing dummy audio in it's place etc.
Is there any module / SDK / Framework in Python to achieve this?
Thanks in advance