Skip to content
Cameron Mills

All projects

Word times from the voice and a beat grid from the music

Timing

Part of Digital media system

faster-whisper times every spoken word, and the engine fits a beat grid to the song, so cuts land on word starts or on beats.

What it does

faster-whisper gives word-level caption timing. The edit engine analyses a song for tempo, a beat grid, downbeats, drops and phrase boundaries. With a voiceover, the transcription sets caption timing, and the voice plays over ducked music.

The check

After the render, the engine finds the cuts in the finished video and compares them with the beat grid.

Stack

  • faster-whisper
  • librosa

How these figures are sourced

The outcome figure is agent-reported: it is taken from a test log or report written by the agents that built and ran the system. The status was read from the edit engine README and the Green Label licence table. Every figure and claim on this page is tied to a source file or a CV line in the site's content.