there are many algs out there to calculate BPM of tracks and they are all flawed, one way or another.
2024-02-22 05337, 2024
mayhem
what works for one musical style, doesn't work for another.
2024-02-22 05353, 2024
mayhem
so, our question is: can a neural network do a better job?
2024-02-22 05313, 2024
diptanil joined the channel
2024-02-22 05341, 2024
diptanil has quit
2024-02-22 05332, 2024
munishk
In my search too, I wasn't able to find an algorithm being used widely for this task. I think I will be needing some data to experiment and explore neural networks for this use case.Would it be possible to get some sample data at this point of time?
2024-02-22 05346, 2024
minimal joined the channel
2024-02-22 05328, 2024
schmias has quit
2024-02-22 05330, 2024
zima_blue has quit
2024-02-22 05348, 2024
zima_blue joined the channel
2024-02-22 05350, 2024
zima_blue has quit
2024-02-22 05339, 2024
mayhem
sure.
2024-02-22 05340, 2024
zima_blue joined the channel
2024-02-22 05306, 2024
mayhem
for starters, use some of your own music and convert it to wav files and run it through the alg. and if you get some promising results, I'll build a larger dataset
2024-02-22 05350, 2024
diptanil joined the channel
2024-02-22 05332, 2024
munishk
thanks, I will start experimenting and reach out soon with some results
2024-02-22 05339, 2024
mayhem
ok
2024-02-22 05313, 2024
zima_blue
Hi all, I'm working on integrating MusicBrainz into a Letterboxd for music app. Noticed its search results tend to be broader than what Spotify's API offers.
2024-02-22 05320, 2024
zima_blue
Considering using Spotify for initial searches and mapping those to MusicBrainz entities. Thoughts?
2024-02-22 05329, 2024
zima_blue
Alternatively, thinking about customizing the SOLR engine on a MusicBrainz server for tighter search results. Is this feasible?
2024-02-22 05337, 2024
zima_blue
Would appreciate any insights or advice on these approaches or other ideas!
2024-02-22 05306, 2024
mayhem
hi!
2024-02-22 05326, 2024
mayhem
when you say broad search results, what do you mean? do you have an example?
I know that's biased, but i'm wanting something that would default towards more popular results
2024-02-22 05356, 2024
mayhem
ok, yeah, we've gotten that complaint before and it makes sense.
2024-02-22 05307, 2024
mayhem
and yeah, the answer is to add popularity to the data, which should solve the problem.
2024-02-22 05341, 2024
mayhem
do you have the MBID for that recording to hand?
2024-02-22 05322, 2024
mayhem
b5e1e12f-8832-4ba4-b772-de15e2db2009 ?
2024-02-22 05354, 2024
zima_blue
yep
2024-02-22 05305, 2024
mayhem
ok, let me try a few things.
2024-02-22 05319, 2024
zima_blue
awesome. much appreciated
2024-02-22 05322, 2024
mayhem
hmmm. that track is not in our recording popularity data.
2024-02-22 05338, 2024
zima_blue has quit
2024-02-22 05351, 2024
mayhem
for a 2015 release, it should be. odd.
2024-02-22 05315, 2024
zima_blue joined the channel
2024-02-22 05349, 2024
mayhem
lucifer: do you know when the last time was that we calculated recording popularity? or is that being done periodically?
2024-02-22 05358, 2024
mayhem
zima_blue: because what could be done is to take all the search results and then match them against recording popularity and then sort based on that. that ought to move that track near the top.
2024-02-22 05333, 2024
mayhem
but we're not really ready to release that data -- and the given track isn't in that dataset in the first place, so we first need to see what is going on with that dataset. lucifer will know when he's around.
2024-02-22 05344, 2024
zima_blue
cool. thanks for the context. i'll keep an eye out for a response
2024-02-22 05302, 2024
relaxoMob has quit
2024-02-22 05328, 2024
relaxoMob joined the channel
2024-02-22 05304, 2024
diptanil joined the channel
2024-02-22 05359, 2024
diptanil has left the channel
2024-02-22 05345, 2024
diptanil joined the channel
2024-02-22 05358, 2024
munishk
@mayhem I also have a doubt if the goal is to find out the highest bpm value throughout the music or the one that remains for majority of the music?
mayhem: we do it weekly, its broken currently because of the recording mbid i fixed earlier today. i'll initiate a new dump and request the data again tomorrow once the dump is imported to spark.
2024-02-22 05340, 2024
zima_blue has quit
2024-02-22 05301, 2024
zima_blue joined the channel
2024-02-22 05316, 2024
relaxoMob has quit
2024-02-22 05354, 2024
lucifer
diptanil: hi! the metabrainz notification system is quite a difficult project idea. i would suggest to get familiar with at least one of the projects, maybe ListenBrainz because that's where we'll start using it immediately, first.
lucifer: could the "brokenness" of the similar recordings by caused by the problem you fixed? because zima_blue's example track isn't in the DB, despite being from a popular album.
2024-02-22 05303, 2024
lucifer
mayhem: similarity data hasn't been generated in a while, but popularity yes.
2024-02-22 05349, 2024
mayhem
I swear my dyslexia is getting worse. sigh.
2024-02-22 05324, 2024
mayhem
any idea why a popular track might be missing from the popular recordings data?
2024-02-22 05330, 2024
lucifer
zima_blue: fwiw if i understand correctly letterboxd for music would not be much different from what ListenBrainz is.
2024-02-22 05314, 2024
lucifer
we batch recordings into 5-10k while inserting data in db, if any single row is problematic entire batch fails.
2024-02-22 05326, 2024
lucifer
so that would be my first guess.
2024-02-22 05336, 2024
mayhem
ok, cool. then ping me when the data set is run and we'll have another look.
2024-02-22 05349, 2024
lucifer
will do
2024-02-22 05307, 2024
lucifer
also, you need to check if the recording is a canonical recording.
2024-02-22 05326, 2024
mayhem
I did. it was.
2024-02-22 05333, 2024
lucifer
ah cool
2024-02-22 05316, 2024
lucifer
i just grepped the error logs with the mbid you had posted, its there.
2024-02-22 05326, 2024
lucifer
it was part of a batch that failed to insert.
2024-02-22 05341, 2024
mayhem
good good. I'll follow up with zima when they return
2024-02-22 05341, 2024
lucifer
so most probably should be fixed the next time we generate this data.
2024-02-22 05330, 2024
lucifer
let me do a couple of PR merges and then i'll do a release followed by creating new dumps
2024-02-22 05353, 2024
lucifer mayhem: does this make sense? https://github.com/metabrainz/listenbrainz-server/pull/2777#discussion_r1493296602
2024-02-22 05318, 2024
mayhem
yes it does.
2024-02-22 05343, 2024
lucifer
cool, i'll go ahead and merge then.
2024-02-22 05350, 2024
mayhem
hang on.
2024-02-22 05301, 2024
mayhem
let me re-write the sentence now that I understand the intent
2024-02-22 05310, 2024
lucifer
great, thanks!
2024-02-22 05326, 2024
mayhem
"Deleted listens present a tricky problem in this setup, since they are not included in the incremental dumps. To get a fully accurate list of listens, with deleted listens removed, you'll need to re-import a full dump." ??
lucifer: Thanks for the help. If I understand ListenBrainz correctly, I believe iCheckMusic has some overlap but there are also differences. iCheckMusic focuses more on reviewing/reflecting
2024-02-22 05308, 2024
zima_blue
There’s also an element of organizing: favoriting things, marking you want to listen to something later, lists, etc
2024-02-22 05309, 2024
BrainzGit
[listenbrainz-android] 14tmose1106 opened pull request #372 (03main…MOBILE-192-sort-collections): MOBILE-192: Sort Collections by Name/Title by Default https://github.com/metabrainz/listenbrainz-androi…
entire listen history, minimum 10 listens of artist threshold
2024-02-22 05322, 2024
zima_blue has quit
2024-02-22 05338, 2024
zima_blue joined the channel
2024-02-22 05323, 2024
minimal has quit
2024-02-22 05332, 2024
zima_blue has quit
2024-02-22 05332, 2024
aerozol
lucifer: holy shit
2024-02-22 05334, 2024
aerozol
game changer!!
2024-02-22 05319, 2024
aerozol
A whole stack of albums I have to go listen to now/didn’t know were out!
2024-02-22 05339, 2024
aerozol
I’ll ask Discord and #musicbrainz for feedback too
2024-02-22 05332, 2024
yellowhatpro has quit
2024-02-22 05351, 2024
zima_blue joined the channel
2024-02-22 05319, 2024
aerozol[m] joined the channel
2024-02-22 05319, 2024
aerozol[m]
mayhem: I think it’s an excellent idea for you to ping Glenn if you’re keen! Since we follow each other you can also PM him from any of the MB accounts
2024-02-22 05311, 2024
aerozol[m]
I haven’t directly asked him to contribute because I feel he might be looking for paid work right now, so that feels weird. But that’s a discussion you may be able to have!
2024-02-22 05351, 2024
diptanil has quit
2024-02-22 05350, 2024
mthal has quit
2024-02-22 05317, 2024
zima_blue has quit
2024-02-22 05305, 2024
aerozol
p.s. he may also be spoilt for data haha, after having direct access to Spotify for so long, but we can promise other benefits (like not scrapping a bunch of work on a whim)
2024-02-22 05338, 2024
mayhem
ok, I'll see about doing that tomorrow.
2024-02-22 05340, 2024
fletchto99 has quit
2024-02-22 05306, 2024
fletchto99 joined the channel
2024-02-22 05321, 2024
aerozol
lucifer: I think we broke the week/month/3 months filter for Fresh Releases :)
2024-02-22 05306, 2024
mayhem
i like the changes, much better
2024-02-22 05344, 2024
aerozol
I posted the changes to the socials for feedback, always good to drive traffic to check out Fresh Releases anyway
2024-02-22 05309, 2024
aerozol
from @MetadataIsMyDrug on Discord: My thoughts: Too much for me. But for others it wasn’t enough before, and too much is better than not enough if those are the two options. But my tastes have shifted a number of times and I have very little interest in a lot of what I see now, and some days have up to 14 releases now. 😮
