| --- |
| library_name: maubert |
| license: mit |
| tags: |
| - acoustic-unit-discovery |
| - hubert |
| - maubert |
| - speech |
| language_bcp47: |
| - ab |
| - am |
| - ba |
| - be |
| - bg |
| - bn |
| - ca |
| - ckb |
| - cs |
| - cv |
| - dv |
| - el |
| - eu |
| - gn |
| - ha |
| - hi |
| - hsb |
| - hu |
| - hy-AM |
| - id |
| - it |
| - ja |
| - ka |
| - kk |
| - kmr |
| - ko |
| - ky |
| - lij |
| - lt |
| - ml |
| - mn |
| - mr |
| - mt |
| - myv |
| - nan-tw |
| - nl |
| - pa-IN |
| - pl |
| - pt |
| - ro |
| - ru |
| - rw |
| - sk |
| - sl |
| - sq |
| - sr |
| - sv-SE |
| - tk |
| - tt |
| - ug |
| - ur |
| - uz |
| - vi |
| - yo |
| - yue |
| --- |
| |
| # 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](https://aclanthology.org/2026.acl-long.24/) at ACL 2026. |
|
|
| You can load it with [`maubert`](https://github.com/bootphon/maubert): |
|
|
| ```python |
| from maubert import MauBERTFeat |
| |
| model = MauBERTFeat.from_pretrained("coml/maubert-feat") |
| ``` |
|
|
| Check out the [`maubert`](https://github.com/bootphon/maubert) repository if you are interested in further retraining |
| or fine-tuning, and the [corresponding paper](https://aclanthology.org/2026.acl-long.24/) for our results. |
|
|
| ## 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`](https://huggingface.co/datasets/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", |
| } |
| ``` |
|
|
