Project AURIONAI Use-Cases Research & Innovation
Meta
speech recognitionfamily

HuBERT

Self-supervised speech representation model that learns by predicting masked hidden units; a backbone for speech recognition and other speech tasks.

MetaMetaUSA
Figure from the HuBERT paper: diagram of HuBERT predicting hidden cluster labels for masked speech frames.
Levelfamily
Classspeech recognition
Parametersnot in the notes
Contextnot in the notes
Released14 Jun 2021
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Lineage

20212022hubert-base-ls960hubert-base-ls960, Jun 2021hubert-large-ll60k, Jun 2021hubert-xlarge-ll60k, Jun 2021
Metahubert-base-ls960 belongs to this familyspeech recognition14 Jun 2021
Metahubert-large-ll60k belongs to this familyspeech recognition14 Jun 2021
Metahubert-xlarge-ll60k belongs to this familyspeech recognition14 Jun 2021
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Self-supervised speech representation learningexemplar

Identity

Developer
Meta
Family
not in the notes
Released
14 Jun 2021 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer self-supervised masked prediction of hidden units
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
Base, Large and X-Large; Large also published fine-tuned on 960 h of LibriSpeech (hubert-large-ls960-ft).
Context length
not in the notes
Input
audio
Output
not in the notes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
English (LibriSpeech and Libri-Light pre-training)
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2106.07447 https://arxiv.org/abs/2106.07447
  2. github.com/facebookresearch/fairseq/tree/main/examples/h... https://github.com/facebookresearch/fairseq/tree/main/examples/hubert
  3. huggingface.co/facebook/hubert-large-ls960-ft https://huggingface.co/facebook/hubert-large-ls960-ft

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "HuBERT", https://aurion.semai.id/models/meta-hubert/, records of October 2026.