Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: "en"
|
3 |
+
inference: false
|
4 |
+
tags:
|
5 |
+
- Vocoder
|
6 |
+
- HiFIGAN
|
7 |
+
- speech-synthesis
|
8 |
+
- speechbrain
|
9 |
+
license: "apache-2.0"
|
10 |
+
datasets:
|
11 |
+
- LibriTTS
|
12 |
+
---
|
13 |
+
|
14 |
+
|
15 |
+
<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>
|
16 |
+
<br/><br/>
|
17 |
+
|
18 |
+
# Vocoder with HiFIGAN Unit trained on LibriTTS
|
19 |
+
|
20 |
+
This repository provides all the necessary tools for using a [scalable HiFiGAN Unit](https://arxiv.org/abs/2406.10735) vocoder trained with [LibriTTS](https://www.openslr.org/141/).
|
21 |
+
|
22 |
+
The pre-trained model take as input discrete self-supervised representations and produces a waveform as output. Typically, this model is utilized on top of a speech-to-unit translation model that converts an input utterance from a source language into a sequence of discrete speech units in a target language.
|
23 |
+
To generate the discrete self-supervised representations, we employ a K-means clustering model trained on HuBERT hidden layers, with `k=1000`.
|
24 |
+
|
25 |
+
## Install SpeechBrain
|
26 |
+
|
27 |
+
First of all, please install tranformers and SpeechBrain with the following command:
|
28 |
+
|
29 |
+
```
|
30 |
+
pip install speechbrain transformers
|
31 |
+
```
|
32 |
+
|
33 |
+
Please notice that we encourage you to read our tutorials and learn more about
|
34 |
+
[SpeechBrain](https://speechbrain.github.io).
|
35 |
+
|
36 |
+
|
37 |
+
### Using the Vocoder
|
38 |
+
|
39 |
+
```python
|
40 |
+
import torch
|
41 |
+
from speechbrain.inference.vocoders import UnitHIFIGAN
|
42 |
+
|
43 |
+
hifi_gan_unit = UnitHIFIGAN.from_hparams(source="speechbrain/hifigan-hubert-l1-3-7-12-18-23-k1000-LibriTTS", savedir="pretrained_models/vocoder")
|
44 |
+
codes = torch.randint(0, 99, (100, 1))
|
45 |
+
waveform = hifi_gan_unit.decode_unit(codes)
|
46 |
+
|
47 |
+
```
|
48 |
+
|
49 |
+
|
50 |
+
### Inference on GPU
|
51 |
+
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
|
52 |
+
|
53 |
+
|
54 |
+
### Limitations
|
55 |
+
The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
|
56 |
+
|
57 |
+
#### Referencing SpeechBrain
|
58 |
+
|
59 |
+
```
|
60 |
+
@misc{SB2021,
|
61 |
+
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 },
|
62 |
+
title = {SpeechBrain},
|
63 |
+
year = {2021},
|
64 |
+
publisher = {GitHub},
|
65 |
+
journal = {GitHub repository},
|
66 |
+
howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
|
67 |
+
}
|
68 |
+
```
|
69 |
+
|
70 |
+
#### About SpeechBrain
|
71 |
+
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.
|
72 |
+
|
73 |
+
Website: https://speechbrain.github.io/
|
74 |
+
|
75 |
+
GitHub: https://github.com/speechbrain/speechbrain
|