Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

maroofy.com

Post reply on HN
Print view View original

401–410 of 444 posts

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

#401

Post by subtech »

turkeygizzard wrote: post #96
subtech wrote: post #33

Earlier quoted context omitted.

Hey thanks for the feedback! I definitely have a lot of improvement to do on the model, it currently performs better for some styles/genres of music than others. But the model architecture I'm using is kinda outdated as well, gotta iterate on it more to improve it further! I'm also thinking of letting users upvote/downvote results, which can also help improve quality on the ranking side.

Wanted to hop on and say this is amazing, thank you for sharing this! Also agree that it seems that it's really good at finding literally similar sounding songs, but not what I would expect a friend to recommend (this is both good and bad I guess). As someone else said, this is already way better than my spotify recs

ty for ur kind words! <3

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

#402

Post by subtech »

robbiemitchell wrote: post #390

This is a project I've always dreamed of building! Already pretty excited about some of the recommendations I'm getting in some niche genres. Feature request: allow me to auth Spotify and click a button next to each track to add a track to a "Maroofy Recs" playlist

Noted! A lot of people have asked for a playlist support, definitely shipping that soon!

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

#403

Post by subtech »

nightkall wrote: post #336

Fantastic tool, thanks for making it! As others said, it would be a nice option to export it as a playlist for Spotify/Apple/Youtube or a .txt file with "Artist - Track name" in each line. Then you can import the txt file into a playlist converter tool like www.tunemymusic.com and play it in your favorite music service. Mine is discoverquickly.com where you can listen Spotify playlists fast with mouseover, and discov…

Playlist + some sort of auto-playing mechanic is coming!

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

#404

Post by subtech »

agentwiggles wrote: post #400
AlecSchueler wrote: post #392

This is actually great, one of the most promising recommendation algorithms I've come across. I love that it's working by sound. So often eg Spotify will insist I check out other bands in the same "scene" or from the same era as other artists I like, and in genres as broad as "70s rock" it can be really tiring. One of the first tracks I tried was Natural Woman by Carole King. I love that it recommended other slow but…

I'm enjoying it a lot too, I've always been a bit frustrated by what you describe with Spotify. It's like it's keying more on genre than sound, which has both pros and cons, but ends up giving me a lot of music that is nominally in the same genre but missing the qualities I like about a certain song. Probably my favorite song of all time is Close to the Edge, by Yes. Spotify will happily provide me with tons of recom…

Thank you so much! With an improved model, things should get a lot better! :D

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

#406

Post by m3kw9 »

rohith2506 wrote: post #382

Tried few recommendations and can definitely use an alternative for Spotify radio. Seems like you are dodging the question of data access and I am not sure why. Even running an intelligent scraper to download 120M song previews sounds too complex and might take days to months as you have to rotate IPs and not bombard the server all the time. If you manage to do that, kudos. That itself is a great achievement. If not,…

He’s not obligated to tell us if he knows it’s an edge he wants to keep

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

#409

Post by rohith2506 »

m3kw9 wrote: post #406
rohith2506 wrote: post #382

Tried few recommendations and can definitely use an alternative for Spotify radio. Seems like you are dodging the question of data access and I am not sure why. Even running an intelligent scraper to download 120M song previews sounds too complex and might take days to months as you have to rotate IPs and not bombard the server all the time. If you manage to do that, kudos. That itself is a great achievement. If not,…

He’s not obligated to tell us if he knows it’s an edge he wants to keep

I don’t think I agree with that. If he is scraping, all he can say is yes. The details of the scraper is proprietary and that’s his edge for sure.

If not and he found an unauthorized source of retrieving information, this reveals a serious security breach in iTunes API and it’s my valid concern as a paid customer.

120M is a huge number and it’s not even text. It’s media

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

#410

Post by yunwal »

exikyut wrote: post #360
proc0 wrote: post #354

Earlier quoted context omitted.

Also would like to know. I can't even listen to the full songs, and assuming I have to pay. I can't imagine buying 120 million songs, so it has to be some collab with iTunes.

Thinking about both processing time and the difficulty of sustaining 120M downloads' worth of programmatic access, I wouldn't be surprised if this is actually trained on the track previews.

I’m almost positive it is. If you put in a song with a bunch of different styles, sections (e.g. bohemian rhapsody) the suggestions match the preview
Post reply on HN