You can deploy this model and start earning money today!

coml/
maubert-feat

Name: maubert-feat
Rating: 2.5 (75 reviews)

maubert

safetensors

acoustic-unit-discovery

hubert

speech

mit

Views

No views yet

MauBERT-feat

MauBERT-feat is a speech model adapting a pre-trained HuBERT base model to predict frame-level articulatory features on a subset of 788 hours and 55 languages of Common Voice 16.1 leveraging the phone annotations from VoxCommunis. It was introduced by the MauBERT paper at ACL 2026.

You can load it with maubert:

python

from maubert import MauBERTFeat

model = MauBERTFeat.from_pretrained("coml/maubert-feat")

Check out the maubert repository if you are interested in further retraining or fine-tuning, and the corresponding paper for our results.

The quantisation models used to turn its features into the pseudo-labels of the paper are released in coml/maubert-quantisers.

Files:

model.safetensors and config.json: HuggingFace Transformers checkpoint and config.

The manifests, phone alignments, language table and phone inventories used to train this model are released separately in coml/vox-communis-artifacts. The inventories are required to reduce the phone head when extracting features from the phone projection layer:

python

from huggingface_hub import snapshot_download

data_dir = snapshot_download("coml/vox-communis-artifacts", repo_type="dataset")
# then pass f"{data_dir}/canonical_inventories.jsonl" as `inventory_file`

Citing

bibtex

@inproceedings{ortiztandazo-etal-2026-maubert,
    title = "{M}au{BERT}: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery",
    author = "Ortiz Tandazo, Angelo  and
      Khentout, Manel  and
      Benchekroun, Youssef  and
      Hueber, Thomas  and
      Dupoux, Emmanuel",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.acl-long.24/",
    doi = "10.18653/v1/2026.acl-long.24",
    pages = "568--585",
    ISBN = "979-8-89176-390-6",
}