|
--- |
|
language: |
|
- fr |
|
- en |
|
inference: false |
|
tags: |
|
- speech-to-speech-translation |
|
- speechbrain |
|
license: apache-2.0 |
|
datasets: |
|
- 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](https://arxiv.org/abs/2201.03713) dataset. |
|
The implementation is based on [Textless Speech-to-Speech Translation](https://arxiv.org/abs/2112.08352) and [Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentatio](https://arxiv.org/abs/2204.02967) 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](https://speechbrain.github.io). |
|
|
|
|
|
### Perform speech-to-speech translation (S2ST) with S2UT model and the Vocoder |
|
```python |
|
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 |
