I love learning new languages. One problem I always stumble across is finding interesting/advanced content with subtitles. One solution to that is using a well optimized reimplementation of OpenAI Whisper called Faster Whisper, which can transcribe videos using AI.
Go to this Google Colab and enjoy!
Using the free T4 GPU, I can generally transcribe a video in 10% of its duration using the largest model! Here's a list of videos, their duration, and the execution time of the code. (I will write this table in the future)
The videos are saved along with their .info.json, which makes them compatible with the amazing Jellyfin YouTube Metadata Plugin. Now, with the videos inside your Jellyfin, you can study on whatever device you want! Your smartphone, TV, laptop, you name it.
This is a fork from lewangdev, which itself is a fork of ArthurFDLR, i just added a few lines to make it compatible with jellyfin. Thank you guys for making this simple yet extremely useful Google Colab notebook!