4min chapter

MLOps.community  cover image

Bringing Audio ML Models into Production // Valerio Velardo // MLOps Coffee Sessions #90

MLOps.community

CHAPTER

Transform Spectra Into ML Spectrograms

The problem with all your data is that if you are dealing with ro oudiot, for example, a waf i, this is highly, highly dimensio dimensional. It's very difficult to take aa very long piece of ro ordio and pass it into a dep lerning modle because the dimensionality is enormous. In other words, we need to have representations of the odio that's meaninful enough, and at the same time that's compact enough so that the models can handle this information. Music processing is something so peculiar, and you have to have a set of scales that are quite unique in order to work in this space.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode