---
license: apache-2.0
datasets:
- librispeech_asr
language:
- en
library_name: sklearn
---

<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=medium" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
<br/><br/>

# K-means (Quantization)
## <font color="red">  Work In Progress ....  </font>

This folder contains  pre-trained  K-means  models for the LibriSpeech Dataset.
The model serves to quantize self-supervised representations into discrete representation. Thus representations can be used as a discrete audio input for various tasks including classification, ASR and speech gneration.
It supports  kmeans models using the features from  HuBERT, WAVLM or Wav2Vec.

### Training
The model was trained with SpeechBrain.
To train it from scratch follow these steps:
1. Clone SpeechBrain:
```bash
git clone --branch unstable-v0.6 https://github.com/speechbrain/speechbrain/
```
2. Install it:
```bash
cd speechbrain
pip install -r requirements.txt
pip install -e .
```

3. Run Training:
```bash
cd recipes/LibriSpeech/quantization/
pip install -r rextra-requirements.txt
python train.py hparams/train_with_[ssl_model].yaml --data_folder=your_data_folder
```

You can find our training results (models, logs, etc) [here](https://huggingface.co/speechbrain/SSL_Quantization).

### Limitations
The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

#### Referencing SpeechBrain

```
@misc{SB2021,
    author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
    title = {SpeechBrain},
    year = {2021},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
  }
```

#### About SpeechBrain
SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains.

Website: https://speechbrain.github.io/

GitHub: https://github.com/speechbrain/speechbrain