Report Get Physical Music built from the datasets alone

Yes. Get Physical Music has 13 videos listed in datasets used to train and test AI models.

This page only knows about the videos the datasets list. To check every upload on the channel:

Used for training and testing 13

videos in AudioSet

A list of about a million ten-second YouTube clips, each labelled with the sounds in it, that Google published in 2017. Labs use it to train and test general audio and music models.

Including M.A.N.D.Y. - Gizmo, Audiofly vs. Big Bully - I'll Tell Ya, H.O.S.H. with Adriano - Don Alfredo

Used for testing 1

video in MusicCaps

A set of 5,521 ten-second music clips from YouTube, each with a written description, that Google published in 2023. It is the standard test set for text-to-music models.

Including M.A.N.D.Y. - Gizmo

AudioSet 13 videos, 13 rows

M.A.N.D.Y. - Gizmo

Clip 270s to 280s · Open clip on YouTube · Labels: Music, Techno, Zing

youtube_video 3Wdxjm-h36w · row eval:3Wdxjm-h36w:270:280

AudioSeteval

Audiofly vs. Big Bully - I'll Tell Ya

Clip 480s to 490s · Open clip on YouTube · Labels: Music, Drum machine

youtube_video 06v2xA4FeCo · row unbalanced_train:06v2xA4FeCo:480:490

AudioSetunbalanced_train

H.O.S.H. with Adriano - Don Alfredo

Clip 320s to 330s · Open clip on YouTube · Labels: Music, Drum machine

youtube_video 4eXaYP_dDKE · row unbalanced_train:4eXaYP_dDKE:320:330

AudioSetunbalanced_train

Julio Victoria - Impermanent (Official Music Video)

Clip 30s to 40s · Open clip on YouTube · Labels: Funk, Music

youtube_video 4f3eRW8DTkM · row unbalanced_train:4f3eRW8DTkM:30:40

AudioSetunbalanced_train

05. Todd Terry - Presents Sound Design Searchin' (DJ T. Edit)

Clip 30s to 40s · Open clip on YouTube · Labels: Music

youtube_video 81t4bzSjlgA · row unbalanced_train:81t4bzSjlgA:30:40

AudioSetunbalanced_train

Bedouin - Hologram (Original Version)

Clip 0s to 10s · Open clip on YouTube · Labels: Music

youtube_video 9wH9GXlyhmw · row unbalanced_train:9wH9GXlyhmw:0:10

AudioSetunbalanced_train

07. Kris Wadsworth - Gutter Pimp

Clip 190s to 200s · Open clip on YouTube · Labels: Scratching (performance technique), Music

youtube_video BbG4-rn56o0 · row unbalanced_train:BbG4-rn56o0:190:200

AudioSetunbalanced_train

Wankelmut - Wood & Wine

Clip 30s to 40s · Open clip on YouTube · Labels: Music

youtube_video FWmNoXBYcaA · row unbalanced_train:FWmNoXBYcaA:30:40

AudioSetunbalanced_train

Storm Queen - Look Right Through

Clip 250s to 260s · Open clip on YouTube · Labels: Music, Drum machine

youtube_video l5Kzg-oM0Is · row unbalanced_train:l5Kzg-oM0Is:250:260

AudioSetunbalanced_train

10. Sandeman - Drop That Thing

Clip 170s to 180s · Open clip on YouTube · Labels: Music, Reggae

youtube_video njxEQBirXIg · row unbalanced_train:njxEQBirXIg:170:180

AudioSetunbalanced_train

DJ Linus - Who Stole The Soul (Luna City Express Remix)

Clip 120s to 130s · Open clip on YouTube · Labels: House music

youtube_video pSStZ8YXuFM · row unbalanced_train:pSStZ8YXuFM:120:130

AudioSetunbalanced_train

Smash TV - When I (Ruede Hagelstein Remix)

Clip 90s to 100s · Open clip on YouTube · Labels: Disco, Music

youtube_video tLx-4Xleytg · row unbalanced_train:tLx-4Xleytg:90:100

AudioSetunbalanced_train

09. Aaaron - Splendid

Clip 210s to 220s · Open clip on YouTube · Labels: Music, Drum machine

youtube_video zWjz96gRqbI · row unbalanced_train:zWjz96gRqbI:210:220

AudioSetunbalanced_train

MusicCaps 1 videos, 1 rows

M.A.N.D.Y. - Gizmo

“This song contains a synth melody that sounds a little in the background slowly coming more into focus. This sound is full of reverb. Other synth sounds are playing pads and experimental pluck sounds. A glass sound is being played as a hi hat and a noise snare sound takes a lot of space with sounds panned to the left and right side of the speakers. This song may be playing in a club.”

Clip 270s to 280s · Open clip on YouTube

youtube_video 3Wdxjm-h36w · row 3Wdxjm-h36w:270:280

MusicCaps

What this means

Last reviewed 2026-09-24.

Presence in a public research dataset shows that a clip of your recording was listed by academic or industry researchers as material for building or testing audio models. It does not by itself show which commercial products, if any, used the clip. The legal picture is moving. On 31 July 2026 the Regional Court of Munich I ruled in GEMA's case against Suno (case 42 O 763/25) that reproducing works for training, holding them in a model in retrievable form, and generating similar outputs can each infringe copyright under German and EU law; the judgment is not final and can be appealed. In the United States, Warner Music Group settled its claims against Suno on 25 November 2025 with a licensing deal, while the parallel claims by Universal and Sony were still pending at that point. Since then BMG (12 August 2026) and Believe/TuneCore (8 September 2026) have signed opt-in licensing deals with Suno.

What you can do

3 routes. None is a guarantee.

UK, PRS members. Send PRS for Music your report and ask what collective or licensing route covers your works.
- PRS for Music and Artificial Intelligence, Version 1 (October 2025), 2025-10-01
- PRS for Music: AI and music copyright, 2026-09-24
Germany, GEMA members. GEMA won a first-instance ruling against Suno on 31 July 2026 and has a licensing model. Ask how they apply to your repertoire.
- GEMA: Suno AI and OpenAI, GEMA sues for fair compensation, 2025-01-21
- DLA Piper: GEMA v Suno, Munich Regional Court judgment of 31 July 2026, 2026-08-28
- Music Business Worldwide: Germany's GEMA launches AI Charter, 2024-11-05
Signed to Warner, BMG or Believe/TuneCore. Each has an opt-in licensing deal with Suno. Ask your label what opting in or out means for you and whether any settlement money reaches artists.
- Music Business Worldwide: Warner Music Group settles with Suno, 2025-11-25
- Music Ally: Suno signs another music licensing deal, with BMG, 2026-08-12
- Music Business Worldwide: Suno inks global deal with Believe, 2026-09-08

Keep a copy

Download the evidence (PDF) JSON Check another name

Share this page https://youtrained.com/r/get-physical-music-yt_UCttOBQS6RSh8avmR8vcrB8A

Provenance

JSON export SHA-256 274f14843ed19e2a3879e21b239dabf4aee47f84f6c58649558289604880b4af

Dataset versions indexed

Dataset	File	Rows	Loaded	SHA-256
audioset	balanced_train_segments.csv	8,836	2026-09-24T10:30:36+00:00	`3b83e5ff9ed72cfd…`
audioset	eval_segments.csv	7,848	2026-09-24T10:30:36+00:00	`f7055f53935f70e7…`
audioset	unbalanced_train_segments.csv	1,063,333	2026-09-24T10:30:43+00:00	`bb2dfd5e4f1ced39…`
laion_disco_12m	train-00000-of-00005.parquet	2,464,184	2026-09-24T12:18:19+00:00	`f8b1f0034f8f1e94…`
laion_disco_12m	train-00001-of-00005.parquet	2,464,183	2026-09-24T12:32:29+00:00	`71d78ad14ee3f85d…`
laion_disco_12m	train-00002-of-00005.parquet	2,464,183	2026-09-24T12:49:06+00:00	`0feba570a0e8e73c…`
laion_disco_12m	train-00003-of-00005.parquet	2,464,183	2026-09-24T13:06:37+00:00	`21a77d99fd85ad2f…`
laion_disco_12m	train-00004-of-00005.parquet	2,464,183	2026-09-24T13:24:36+00:00	`6ac5f59958b6b813…`
musiccaps	musiccaps-public.csv	5,521	2026-09-24T10:29:42+00:00	`8cc109ac507b5e5a…`

These pages report where identifiers from public research datasets point. Presence in a dataset is a fact about the dataset, not a claim about the channel or artist, and says nothing about what any company did with the material. This report is informational and is not legal advice. It shows that identifiers matching your work are present in the named public research datasets; it does not establish how any particular company used them. If you are the subject of this page and want it removed, see removals.