We've talked largely about text but there's also stuff pertaining to image and even music maybe just give like a little rundown of what those data sets are. The task basically it's a theme it's predict something something spied predict it by one by one so for image it's normally come with an image size say you know 4k image. On the audio experiment basically we take some audio book data where basically audio book data as well as some speech dataBasically think about in the end it's just wave and you want to know how well your model can accuracy predict or recover those waves information.

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