Replies: 1 comment
-
I'm not sure about file length / file size but recently I used nf-whisper on all these talks. The transcriptions weren't perfect but good enough, given some manual curation. There's a step in the pipeline to extract the audio from the YouTube video URL, but yes, it's quicker if you provide it directly with the mp3 file, yes |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Relatedly, would you recommend converting mp4 files to mp3 files first before running nf-whisper
Beta Was this translation helpful? Give feedback.
All reactions