T
threadgillcom
Hi,I use AWS's speech to text for my college class lectures. The output is a *.json file separated in 2 parts:1. The transcribed, punctuated lecture (which may have 1-5 speakers)Note: this is typically a 5-10k word, unformatted string of sentances. Everything is in the right order, but speakers aren't separated, no paragraphs, etc.2. JSON at the bottom half (tags for each word, which that id the speaker, the confidence of the transcription, etc.)Is there a Word extension, or do I have to spend the next 3 weeks wading through GitHub posts, learning how to setup/configure/use Python/Docker
Continue reading...
Continue reading...