---
license: cc-by-nc-4.0
library_name: pint-infer
pipeline_tag: feature-extraction
base_model: facebook/hubert-base-ls960
tags:
  - speech
  - audio
  - tokenizer
  - hubert
  - speech-tokens
language:
  - en
---

# PINT

**Content is What Remains: Invariant Speech Tokenization from Parallel Utterances** —
[arXiv:2607.19033](https://arxiv.org/abs/2607.19033), accepted at **Interspeech 2026**.

A HuBERT-base encoder fine-tuned on parallel utterances (the same words from different speakers and recording conditions) so that they map to the same frame-level representation. 16 kHz audio in, one 768-d vector per 20 ms frame out; token ids come from k-means codebooks.

## Usage

```bash
pip install git+https://github.com/nyrahealth/PINT
```

```python
from pint_infer import PINTTokenizer

tok = PINTTokenizer.from_pretrained("nyralabs/PINT")
ids = tok.encode("speech.wav", method="kmeans_200")  # one token id per 20 ms
frames = tok.embed("speech.wav")  # (T, 768) float32
```

Methods: `kmeans_50`, `kmeans_100`, `kmeans_200`, `kmeans_250`, `kmeans_500`, `kmeans_1000`.

## Files

| File | Content |
|---|---|
| `model.safetensors`, `config.json`, `preprocessor_config.json` | HuBERT-base encoder and feature extractor |
| `kmeans_<k>.safetensors` | `(k, 768)` k-means cluster centers; assignment is nearest centroid |
| `pint_config.json` | frame rate, codebook list |

k=200 is the codebook size the paper evaluates; the other codebook sizes are provided for convenience.

## Intended use and limitations

English speech. Input is converted to 16 kHz mono. Research and non-commercial use.

## Citation

```bibtex
@misc{wagner2026contentremainsinvariantspeech,
  title         = {Content is What Remains: Invariant Speech Tokenization from Parallel Utterances},
  author        = {Laurin Wagner and Bernhard Thallinger and Miroslav Stankovic and Mario Zusag},
  year          = {2026},
  eprint        = {2607.19033},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.19033},
  note          = {Accepted at Interspeech 2026}
}
```

## License

The weights are released under CC BY-NC 4.0. They are derived from
[facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960), licensed under
the Apache License 2.0; see `NOTICE`.