mirror of
https://github.com/openai/whisper.git
synced 2025-11-24 06:26:03 +00:00
30 lines
990 B
Python
30 lines
990 B
Python
|
|
#declare each video path to track down captures
|
|
#specific folders to monitor:
|
|
# C:\Users\lundg\Videos\Captures
|
|
# "C:\Users\lundg\Videos\Clip Champ"
|
|
# "C:\Users\lundg\Videos\Call of Duty Modern Warfare 3 (2023)"
|
|
# "C:\Users\lundg\Videos\Desktop"
|
|
# "C:\Users\lundg\Videos\SteelSeries Moments"
|
|
# "C:\Users\lundg\Videos\Captures"
|
|
# "C:\Users\lundg\Videos\Fortnite"
|
|
# "C:\Users\lundg\Videos\RealVNC"
|
|
|
|
#essentially any picture of video under C://Users//lundg//Videoo
|
|
|
|
# pictures, audio files and video files(and paths) need to be logged for of all files(videos and pictures in this directories) and store them in a list
|
|
#each file that is tracked with an object should also be logged in a db?
|
|
|
|
|
|
#figure out how to separate audio from video files via an api or cli
|
|
|
|
#example extract audio from video.mp4 and save it as audio.mp3
|
|
|
|
|
|
|
|
|
|
|
|
#user can select a audio file and transcribe it with whisper
|
|
|
|
#figure out how to design a gui in vscode that can front end this
|
|
# |