Omar Khursheed — LessWrong

LESSWRONG
LW

Analysis of Whisper-Tiny Using Sparse Autoencoders

2mo

In this project, I attempted to explore the model Whisper-Tiny from OpenAI, which is a speech transcription model that takes in audio and provides a transcript as output. Here’s an example of transcription

Reference text: CHAPTER SIXTEEN I MIGHT HAVE TOLD YOU OF THE BEGINNING OF THIS LIAISON IN A FEW LINES BUT I WANTED YOU TO SEE EVERY STEP BY WHICH WE CAME I TO AGREE TO WHATEVER MARGUERITE WISHED
Transcription:  Chapter 16 I might have told you of the beginning of this liaison in a few lines, but I wanted you to see every step by which we came. I to agree to whatever Mark Reid wished.
Input features shape: torch.Size([80, 3000])
Audio duration:

... (read 1064 more words →)