Comment on WhisperX — Automated Transcripts w/ Timestamps and Speaker Tagging

<- View Parent
dgdft@lemmy.world ⁨1⁩ ⁨week⁩ ago

You should be able to get decent results from that if you pipe your tracks through demucs first to isolate the vocals.

github.com/adefossez/demucs

source
Sort:hotnewtop