Live data from Hacker News

Show HN: I trained an AI model on 120M+ songs from iTunes

maroofy.com

41–50 of 444 posts

Re: Show HN: I trained an AI model on 120M+ songs from iTunes

#43
I have no idea what metric the AI is using for 'similarity' but this just sounds like random results to me. None of the vocals, style, genre, and so on are in any way similar. When you look at recommendation engines on Spotify and YouTube music they do a much better job at this than this engine. I think maybe if you had access to data that users enjoy you could cross reference them to find patterns and use that to order your results.

Re: Show HN: I trained an AI model on 120M+ songs from iTunes

#44

Earlier quoted context omitted.

I guess he is working with the 30s low rez previews, I know you can download them with the Spotify API. Apple Music should be similar.

Wouldn't this still be about 36 terabytes of data?

Meh, you can store that on a single d3en.2xlarge for $780.

Re: Show HN: I trained an AI model on 120M+ songs from iTunes

#45
post #5

I searched for "Hot Chip" and all the recommendations were other Hot Chip songs... is that normal? I was expecting different artists, and honestly not expecting any songs by the same artist.

Pop in a specific Hot Chip song and it'll work better I reckon
Post reply on HN