muzic VS beets

We open our code and checkpoint here: muzic/getmusic at main · microsoft/muzic (github.com)

Code: https://github.com/microsoft/muzic

There's a lot of research right now into music generation (example) that could potentially lead to songs completely written, performed, and produced by software. While I don't think those will be topping the charts, the same tech could definitely be used by humans to generate and expand on ideas, and the success of things like Twitter bots powered by GPT-3 makes me think there could be a niche for botpop. On the extreme end, imagine a service like Pandora, except it generates brand new songs tailored to your preferences.

Muzic (https://github.com/microsoft/muzic) is a research project on AI music that empowers music understanding and generation with deep learning and artificial intelligence. Muzic was started by some researchers from Microsoft Research Asia.

We initially release the code of 5 research work: MusicBERT, PDAugment, DeepRapper, SongMASS, and TeleMelody. We will release the code of more research work in the future.

I was always frustrated that there is no solid source for synced lyrics that also offers decent API support. There is good ol' Crintsoft's MiniLyrics that is thankfully free software, was what I used a lot in my childhood, but unfortunately the API is highly obfuscated. Another popular choice is the Musixmatch API, which has a very large database of synced lyrics, but with "free" API that are reverse-engineered from their app, you will quickly run into rate-limit.

That's why I created LRCLIB. It's aimed to provide completely free synchronized lyrics for everyone, especially for FOSS music players, with zero profit intention. It currently has nearly 3,000,000 (not deduplicated) lyrics in database. You can also contribute to the database by adding and syncing lyrics for your favorite songs using the LRCGET client.

I'm trying my best to make LRCLIB server-side code open-source as soon as possible. But right now, full LRCLIB's database dumps have already been uploaded regularly and publicly, which are simply sqlite3 files. Feel free to download, look at or do anything you want with the database at https://lrclib.net/db-dumps.

Many open-source projects have already begun integrating LRCLIB, including:

- beets - music library metadata management (https://github.com/beetbox/beets)

I just ssh onto my server and use beets to remotely organize my navidrome collection and edit metadata. Beets has lots of auto-tagging features and I rarely need to edit anything manually. Works great if you are ok with using the command line.

You could try https://github.com/beetbox/beets but it seemed very manual and extremely slow. I had better luck with Picard.

Honestly? I use https://beets.io/ to organise all my FLAC on my NAS.

I expose the /Music directory over NFC.

I use https://kodi.tv/ to stream music to my amp. I manually pick the album I want to listen to.

Kodi also has a fairly reasonable web UI.

Keep it simple.

If you're technically inclined, there's beets.

You should check out beets.

Yes, you have the torrent client call beets.io on the folder and have beets configured.