Created
April 22, 2023 20:34
-
-
Save Shelob9/c28929fcce324e841c3845377b4ebbd4 to your computer and use it in GitHub Desktop.
Download YouTube video's audio and transcribe with Whisper
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import pytube as pt | |
| import whisper | |
| # download mp3 from youtube video (Two Minute Papers) | |
| yt = pt.YouTube("https://www.youtube.com/watch?v=dd1kN_myNDs") | |
| stream = yt.streams.filter(only_audio=True)[0] | |
| stream.download(filename="audio_english.mp3") | |
| # load large wisper model | |
| model = whisper.load_model("large") | |
| # transcribe | |
| result = model.transcribe("audio_english.mp3") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment