5 comments

[ 2.8 ms ] story [ 29.6 ms ] thread
Author here, available for questions
Whisper will hallucinate on audio segments that don't have any speech. VAD mitigates that. Expect worse results without it, especially on non-English audio.
"Lenovo laptop with Nvidia RTX 4040" 4060?
Is the point that you only need one tool -- ffmpeg -- to both generate transcripts as well as embed those into a video as opposed to having multiple tools?
Do you know if it’s supported on Mac too, with whatever platform specific optimizations like running it on the gpu / with MPS ?