Welcome back to the No BS series on LLMs. Today we’re going to take a fun detour from LLMs and work with some audio processing. This is an important

#3 - Speak To Me! (TTS & STT) - No BS Intro To Developing with LLMs

submited by

Style Pass

2024-07-11 10:30:03

Welcome back to the No BS series on LLMs. Today we’re going to take a fun detour from LLMs and work with some audio processing. This is an important topic since so much of our language is communicated verbally. Being able to process recordings such as meeting recordings and videos as well generate audible responses, such as answers, summaries, or even your own personal morning news podcast will be very useful.

This isn’t going to be a super deep dive into DSP and audio, but rather just introduce you to some of the tools and concepts. If you’d like a deep dive into signals analysis and processing then checkout The Scientist and Engineer’s Guide to Digital Signal Processing.

Working with audio can seem daunting if you haven’t done it before, and it is naturally a very deep topic, but for our purposes it’s pretty quick to get up to working speed with it.

Image By Д.Ильин: vectorization - File:Signal Sampling.png by Email4mobile (talk), CC0, https://commons.wikimedia.org/w/index.php?curid=98587159