chaanks commited on
Commit
c7fbdf3
1 Parent(s): 204769d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +70 -1
README.md CHANGED
@@ -1,3 +1,72 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - LJSpeech
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
19
+
20
+ ## <font color="red"> Work In Progress .... </font>
21
+
22
+ ## Install SpeechBrain
23
+
24
+ First of all, please install tranformers and SpeechBrain with the following command:
25
+
26
+ ```
27
+ pip install speechbrain transformers
28
+ ```
29
+
30
+ Please notice that we encourage you to read our tutorials and learn more about
31
+ [SpeechBrain](https://speechbrain.github.io).
32
+
33
+
34
+ ### Using the Vocoder
35
+
36
+ ```python
37
+ import torch
38
+ from speechbrain.pretrained import UnitHIFIGAN
39
+
40
+ hifi_gan_unit = UnitHIFIGAN.from_hparams(source="chaanks/hifigan-unit-wav2vec2-l7-k128-ljspeech-ljspeech", savedir="tmpdir_vocoder")
41
+ codes = torch.randint(0, 99, (100,))
42
+ waveform = hifi_gan_unit.decode_unit(codes)
43
+
44
+ ```
45
+
46
+
47
+ ### Inference on GPU
48
+ To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
49
+
50
+
51
+ ### Limitations
52
+ The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
53
+
54
+ #### Referencing SpeechBrain
55
+
56
+ ```
57
+ @misc{SB2021,
58
+ 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 },
59
+ title = {SpeechBrain},
60
+ year = {2021},
61
+ publisher = {GitHub},
62
+ journal = {GitHub repository},
63
+ howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
64
+ }
65
+ ```
66
+
67
+ #### About SpeechBrain
68
+ 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.
69
+
70
+ Website: https://speechbrain.github.io/
71
+
72
+ GitHub: https://github.com/speechbrain/speechbrain