Constarium
← Search

Data · dataset · 2026

malerlab/ytsv-unirqvae3-ytsv

Listed in Hugging Face Datasets

YTSV score-image tokens (U-MusT, unirqvae3) RQ-VAE score-image tokens for the YouTube Score Video (YTSV) dataset, the main dataset contribution of U-MusT — 433,920 image–audio pairs from 12,217 score-following videos, 1,341 hours in total, covering roughly 10,000 pieces by more than 2,000 composers.

Description

An order of magnitude larger than any prior music modal-translation corpus. Tokenized with unirqvae3-ytsv at 16x compression.

Roughly 100 GB across 1.1M token files before sharding.… See the full description on the dataset page: huggingface.co/datasets/malerlab/ytsv-unirqvae3-ytsv.

Links

Get the data

Catalogue records · 1

Topics

Stated by source
audio
Inferred from text
Image 75% · Video 75%
Provenance · 1 source records, 12 field assertions
SourceKeyLast seenRaw
Hugging Face Datasetsmalerlab/ytsv-unirqvae3-ytsv12 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · Hugging Faceconnector:huggingface@1.0.0/gated
concepts[field].local:field:computer-science-aimapping · Hugging Faceconnector:huggingface@1.0.0
concepts[modality].hf_modality:audiosource · Hugging Faceconnector:huggingface@1.0.0
concepts[modality].local:modality:audiomapping · Hugging Facevocabulary-mapper@1.0.0keywords['audio']
concepts[modality].local:modality:imageenrichment · Hugging Facekeyword-concept-rules@1.0.0title+description (75%)
concepts[modality].local:modality:videoenrichment · Hugging Facekeyword-concept-rules@1.0.0title+description (75%)
created_datesource · Hugging Faceconnector:huggingface@1.0.0
descriptionsource · Hugging Faceconnector:huggingface@1.0.0/description
licensesource · Hugging Faceconnector:huggingface@1.0.0/tags[license:*]
publication_datesource · Hugging Faceconnector:huggingface@1.0.0
titlesource · Hugging Faceconnector:huggingface@1.0.0/id
updated_datesource · Hugging Faceconnector:huggingface@1.0.0