speechbrain/SSL_Quantization

1---2license: apache-2.03datasets:4- librispeech_asr5language:6- en7library_name: sklearn8---9 10<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>11<br/><br/>12 13# K-means (Quantization)14This folder contains  pre-trained  K-means  models for the LibriSpeech Dataset.15The 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.16It supports  kmeans models using the features from  HuBERT, WAVLM or Wav2Vec.17 18### Training19The model was trained with SpeechBrain.20To train it from scratch follow these steps:211. Clone SpeechBrain:22```bash23git clone --branch unstable-v0.6 https://github.com/speechbrain/speechbrain/24```252. Install it:26```bash27cd speechbrain28pip install -r requirements.txt29pip install -e .30```31 323. Run Training:33```bash34cd recipes/LibriSpeech/quantization/35pip install -r rextra-requirements.txt36python train.py hparams/train_with_[ssl_model].yaml --data_folder=your_data_folder37```38 39You can find our training results (models, logs, etc) [here](https://huggingface.co/speechbrain/SSL_Quantization).40 41### Limitations42The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.43 44#### Referencing SpeechBrain45 46```47@misc{SB2021,48    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 },49    title = {SpeechBrain},50    year = {2021},51    publisher = {GitHub},52    journal = {GitHub repository},53    howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},54  }55```56 57#### About SpeechBrain58SpeechBrain 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.59 60Website: https://speechbrain.github.io/61 62GitHub: https://github.com/speechbrain/speechbrain