cemsubakan commited on
Commit
9bc5f35
1 Parent(s): 38b3772

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +68 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: "en"
3
+ thumbnail:
4
+ tags:
5
+ - Source Separation
6
+ - Speech Separation
7
+ - WSJ02Mix
8
+ - SepFormer
9
+ - Transformer
10
+ license: "apache-2.0"
11
+ datasets:
12
+ - WSJ0-2Mix
13
+ metrics:
14
+ - SI-SNR
15
+ - SDR
16
+
17
+ ---
18
+
19
+ # SepFormer trained on WSJ0-2Mix
20
+
21
+ This repository provides all the necessary tools to perform source separation with a [SepFormer](https://arxiv.org/abs/2010.13154v2)
22
+ model, implemented with SpeechBrain, and pretrained on WSJ0-2Mix dataset. For a better experience we encourage you to learn more about
23
+ [SpeechBrain](https://speechbrain.github.io). The given model performance is 22.5 dB on the test set of WSJ0-2Mix dataset.
24
+
25
+
26
+
27
+ ## Install SpeechBrain
28
+
29
+ First of all, please install SpeechBrain with the following command:
30
+
31
+ ```
32
+ pip install \\we hide ! SpeechBrain is still private :p
33
+ ```
34
+
35
+ Please notice that we encourage you to read our tutorials and learn more about
36
+ [SpeechBrain](https://speechbrain.github.io).
37
+
38
+ ### Transcribing your own audio files
39
+
40
+ ```python
41
+
42
+ from speechbrain.pretrained import separator
43
+ import torchaudio
44
+
45
+ model = separator.from_hparams(source="speechbrain/sepformer-wsj02mix")
46
+
47
+ mix, fs = torchaudio.load("test_mixture.wav")
48
+
49
+ est_sources = model.separate(mix)
50
+ est_sources = est_sources / est_sources.max(dim=1, keepdim=True)[0]
51
+
52
+ torchaudio.save("source1hat.wav", est_sources[:, :, 0].detach().cpu(), 8000)
53
+ torchaudio.save("source2hat.wav", est_sources[:, :, 1].detach().cpu(), 8000)
54
+
55
+ ```
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
+ ```