s2st-transformer-fr-en-hubert-l6-k100-cvss

<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe> <br/><br/>

Speech-to-Unit Translation trained on CVSS

This repository provides all the necessary tools for using a a speech-to-unit translation (S2UT) model using a pre-trained Wav2Vec 2.0 encoder and a transformer decoder on the CVSS dataset. The implementation is based on Textless Speech-to-Speech Translation and Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentatio papers.

The pre-trained model take as input waveform and produces discrete self-supervised representations as output. Typically, a vocoder (e.g., HiFiGAN Unit) is utilized on top of the S2UT model to produce waveform. To generate the discrete self-supervised representations, we employ a K-means clustering model trained on the 6th layer of HuBERT, with k=100.

Install SpeechBrain

First of all, please install tranformers and SpeechBrain with the following command:

pip install speechbrain transformers

Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.

Perform speech-to-speech translation (S2ST) with S2UT model and the Vocoder

import torch
import torchaudio
from speechbrain.inference.ST import EncoderDecoderS2UT
from speechbrain.inference.vocoders import UnitHIFIGAN

# Intialize S2UT (Transformer) and Vocoder (HiFIGAN Unit)
s2ut = EncoderDecoderS2UT.from_hparams(source="speechbrain/s2st-transformer-fr-en-hubert-l6-k100-cvss", savedir="tmpdir_s2ut")
hifi_gan_unit = UnitHIFIGAN.from_hparams(source="speechbrain/tts-hifigan-unit-hubert-l6-k100-ljspeech", savedir="tmpdir_vocoder")

# Running the S2UT model
codes = s2ut.translate_file("speechbrain/s2st-transformer-fr-en-hubert-l6-k100-cvss/example-fr.wav")
codes = torch.IntTensor(codes)

# Running Vocoder (units-to-waveform)
waveforms = hifi_gan_unit.decode_unit(codes)

# Save the waverform
torchaudio.save('example.wav',waveforms.squeeze(1), 16000)

Inference on GPU

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

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