echoprint

There was also EchoPrint (with two incompatible versions), but once EchoNest was bought out by Spotify the public support and development into echoprint died.

When you say the matching is far from perfect, is that at your end or on the part of the echoprint / echonest code?

There used to be an open-source version of this called Echoprint which was shuttered after the company was bought by Spotify in 2012.

That's certainly useful, and what Echoprint and MusicBrainz have tried to do.

The hashing algorithm is provided by Echonest in their Echoprint service and used to compare against their database (hopefully growing after their Spotify acquisition).

But for this dump we exported everything in the official echoprint format so people can use it with the default cluster.

I always thought that using Solr for the index in Echoprint was a bad idea.

Some groups of people tried to keep echoprint alive but I am unaware if it is still used by anyone publicly.

We don't use solr, we use elasticsearch and we also don't hold the unzipped fingerprints in the same format the default echoprint does.

I've worked on the echoprint-codegen algorithm for my current project ( trak.rocks ) and I'm curious about how you reimplemented the matching logic?

Many users of Echoprint in the wild have adapted the python matching logic for their use case as well as changed the hash update rate on the codegen.

However before this can be done, the individual tracks have to picked out - I've not had much luck with Echoprint identifying more than one track at a time.

It's certainly not as speedy as Echoprint, which is both written in C++ and doesn't use an FFT for the locality sensitive hashing, but is quite user friendly.

Just run it through an identifier like Echoprint.