RVQ
Datasets
All datasets matching “RVQ”minimax-music3-rvq-distill-corpus-8k
MiniMax Music3 self-distillation corpus — 11,847 tracks / ~193 h
Paired (audio, RVQ codes, teacher top-50 distributions, DAV latents) traces generated with the official
MiniMax Music3 pipeline (diffusers ModularPipeline), built to train/improve the community audio->codes
RVQ encoder. Fine-tuning SimpleTuner/open-rvq-encoder-minimax-music3-41m-v1 on this corpus pooled with its
original data improves every holdout metric — see… See the full description on the dataset page: https://huggingface.co/datasets/Mothersuperior/minimax-music3-rvq-distill-corpus-8k.minimax-music3-rvq-reverse-distillation
MiniMax Music 3 RVQ Reverse-Distillation Traces
Research traces generated from MiniMax Music 3. Each ZIP contains generated
audio, sampled RVQ codes, teacher sampling logits, conditioning embeddings,
Flow-VAE latents, and source prompt metadata. See campaign-config.json for
generation settings and indexes/ for per-commit manifests.
Dataset statistics
As of 2026-08-16, the uploaded snapshot contains:
2,972 generated songs
91.84 hours of actual generated audio
1… See the full description on the dataset page: https://huggingface.co/datasets/bghira/minimax-music3-rvq-reverse-distillation.mls-speechtokenizer-rvq_0podcast-dialogue-rvq-pairs-3itemslanguage-action-RVQ-CoT-humanML
A chain-of-thought dataset for human movement generation using a RVQ.
Generated from: https://huggingface.co/Wojtekb30/HumanML3D-500ms-FPP-descriptions-CoTs-1
With use of: https://huggingface.co/Wojtekb30/Motion-RVQ-263d-reconstructor-humanML
This dataset can be used to train LLMs into generating chains of thought which contain RVQ movement tokens, allowing generation of human movements.
badilando_2026_01_13_30fps_attnpoolingmlp4_rvq4_nbc512