Today I used #Emacs Lisp to parse Deepgram’s #speech recognition JSON output with utterances, punctuation, and smart format turned on and the #Whisper Large model selected. I turned the words array into a VTT subtitle file with speaker identification (handy for EmacsConf Q&A) and captions limited to roughly 45 characters with punctuation preferred for splitting. It’s way faster than waiting for a CPU-only computer to run Whisper Large on the files. Looking forward to experimenting with this for my personal braindumping too.
sachac's Blog
Interests include: #Emacs, #OrgMode, #elisp, #nodejs, #python, #sketchnotes, #parenting, #cooking, #gardening, #knitting, #sewing, #lego, #captioning, #plover #steno, and #stoic philosophy. Originally from Manila, now in Toronto. Married to a Vim guy (go figure) and raising a 7-year old (editor preference unknown), along with two very loud cats.
Blog: https://sachachua.com (mostly Emacs News these days), sketches: https://sketches.sachachua.com. I also maintain planet.emacslife.com and subed.el
Blog: https://sachachua.com (mostly Emacs News these days), sketches: https://sketches.sachachua.com. I also maintain planet.emacslife.com and subed.el