Why removing 'um' from a recording is harder than it sounds

A tour of erm, a local CLI that removes disfluencies from English speech recordings using faster-whisper, a few detectors that look at the audio directly, and ffmpeg.
142 points by dougcalobrisi 132 days ago doug.sh 69 comments
Summary not yet generated for this article.

Comments (69 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open