AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
AI is creating never before heard sounds! 🎵
Practical AI: Machine Learning, Data Science, LLM
How to Generate a Real Time Audio Model
The models that i'm typically working with are outputting sample by sample. So we're taking about quite a lot of data for things that are gene ing in the raw audio demin thic makes a kind of a challenge, you know, especially a challenge to do it quickly. We actually made like a little web side where we show off two of these models called gandot style. You drop in a yu two blink, and then it replaces the audio of that u two blank with the audio generated from one of these models. I think if you wilk at the paper out of magenta called d d s p, you'll see a really successful version of this, sort
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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