Skip to content

A repo to do interpretability of pre-trained acoustic models

Notifications You must be signed in to change notification settings

er537/whisper_interpretability

Repository files navigation

Interpreting OpenAI's Whisper

This repo contains the code used to produce: https://er537.github.io/blog/2023/09/05/whisper_interpretability.html

NB) This repo is part of ongoing research and thus is not guaranteed to always be in a working state

To get started clone the repo and make a venv: python3 -m venv ./venv source ./venv/bin/activate pip install -r requirements.txt

The repo is structured as follows:

About

A repo to do interpretability of pre-trained acoustic models

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published