---
library_name: maubert
license: mit
tags:
  - acoustic-unit-discovery
  - hubert
  - maubert
  - quantisation
base_model:
  - coml/maubert-feat
  - coml/maubert-phone
  - facebook/hubert-base-ls960
language:
  - deu
  - eng
  - eus
  - fra
  - jpn
  - swa
  - tam
  - tha
  - tur
  - ukr
  - wol
  - cmn
---

# MauBERT quantisers

The quantisation models used to produce the pseudo-labels of
the [MauBERT paper](https://aclanthology.org/2026.acl-long.24/) (ACL 2026). Each of them maps the frame-level features
of one layer of [`coml/maubert-feat`](https://huggingface.co/coml/maubert-feat),
[`coml/maubert-phone`](https://huggingface.co/coml/maubert-phone) or the HuBERT base model to discrete units, and was
fitted on 10 hours of one language.

The fine-tuned models themselves are not released: use [`maubert`](https://github.com/bootphon/maubert) to extract the
features of a pre-trained model, then one of these quantisers to transcribe them into units.

## Layout

```
<model>/<dataset>/<language>/<n_clusters>cl.<ext>
```

`manifest.tsv` lists every file with its base model, layer, quantisation method, dataset, language and number of
clusters.

| model                | base model    | layer           | method         | file  |
|----------------------|---------------|-----------------|----------------|-------|
| `fr-feat-simple`     | MauBERT-feat  | `feat_proj`     | `feat-freq`    | `.pt` |
| `fr-kmeans-feature`  | MauBERT-feat  | `feat_proj`     | `kmeans`       | `.km` |
| `fr-kmeans-hubert_9` | MauBERT-feat  | HuBERT layer 10 | `kmeans`       | `.km` |
| `fr-phone-ft`        | MauBERT-feat  | `phone_proj`    | `phone-ft`     | `.ft` |
| `kmeans-hubert_11`   | HuBERT base   | HuBERT layer 12 | `kmeans`       | `.km` |
| `pr-kmeans-phone`    | MauBERT-phone | `phone_proj`    | `kmeans`       | `.km` |
| `pr-kmeans-ups_proj` | MauBERT-phone | `ups_proj`      | `kmeans`       | `.km` |
| `pr-phone-ft`        | MauBERT-phone | `phone_proj`    | `phone-ft`     | `.ft` |
| `pr-phone-simple`    | MauBERT-phone | `phone_proj`    | `phone-simple` | `.pt` |

The `.km` files are `joblib` pickles of a scikit-learn `MiniBatchKMeans`, the `.ft` files are `torch` state dicts of
the adapted phone-prediction layer, and the other `.pt` files are `torch` tensors. <!-- TODO: record the exact
scikit-learn version the `.km` pickles were written with, they are version-sensitive. -->

## Datasets and languages

| dataset                          | languages                                                                          |
|----------------------------------|------------------------------------------------------------------------------------|
| `discophon`                      | `cmn`, `deu`, `eng`, `eus`, `fra`, `jpn`, `swa`, `tam`, `tha`, `tur`, `ukr`, `wol` |
| `dev-languages`                  | `sw`, `ta`, `th`, `tr`, `uk`                                                       |
| `zrc2017` (ZeroSpeech 2017 test) | `english`, `french`, `german` (LANG1), `mandarin`, `wolof` (LANG2)                 |
| `casual-languages`               | `english`, `french`                                                                |

Every quantiser comes in a 100-cluster variant (370 for `pr-phone-simple`, which uses the full phone inventory of
MauBERT-phone). The `discophon` languages additionally have a variant with as many clusters as the language has phones:
`cmn` 43, `deu` 42, `eng` 40, `eus` 30, `fra` 35, `jpn` 43, `swa` 30, `tam` 30, `tha` 41, `tur` 28, `ukr` 36,
`wol` 40.

## Usage

Extract the features of the corresponding layer with [`maubert`](https://github.com/bootphon/maubert), then transcribe
them with the quantiser:

```bash
hf download coml/maubert-quantisers fr-kmeans-hubert_9/discophon/deu/100cl.km --local-dir quantisers

python -m maubert.features MANIFEST_FILE FEATURE_DIR \
    --type maubert-feat --checkpoint coml/maubert-feat --layer 9

python -m maubert.transcribe FEATURE_DIR \
    quantisers/fr-kmeans-hubert_9/discophon/deu/100cl.km units.jsonl kmeans
```

## 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",
}
```