JorisCos commited on
Commit
de774bb
1 Parent(s): a8a2600

Initial commit

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. README.md +79 -0
  3. pytorch_model.bin +3 -0
.gitattributes CHANGED
@@ -6,3 +6,4 @@
6
  *.tar.gz filter=lfs diff=lfs merge=lfs -text
7
  *.ot filter=lfs diff=lfs merge=lfs -text
8
  *.onnx filter=lfs diff=lfs merge=lfs -text
 
6
  *.tar.gz filter=lfs diff=lfs merge=lfs -text
7
  *.ot filter=lfs diff=lfs merge=lfs -text
8
  *.onnx filter=lfs diff=lfs merge=lfs -text
9
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - asteroid
4
+ - audio
5
+ - ConvTasNet
6
+ datasets:
7
+ - Libri2Mix
8
+ - sep_noisy
9
+ license: CC BY-NC 4.0
10
+ inference: false
11
+ ---
12
+
13
+ ## Asteroid model `JorisCos/ConvTasNet_Libri2Mix_sepnoisy_16k`
14
+
15
+ Description:
16
+
17
+ This model was trained by Joris Cosentino using the librimix recipe in [Asteroid](https://github.com/asteroid-team/asteroid).
18
+ It was trained on the `sep_noisy` task of the Libri2Mix dataset.
19
+
20
+ Training config:
21
+
22
+ ```yml
23
+ data:
24
+ n_src: 2
25
+ sample_rate: 16000
26
+ segment: 3
27
+ task: sep_noisy
28
+ train_dir: data/wav16k/min/train-360
29
+ valid_dir: data/wav16k/min/dev
30
+ filterbank:
31
+ kernel_size: 32
32
+ n_filters: 512
33
+ stride: 16
34
+ masknet:
35
+ bn_chan: 128
36
+ hid_chan: 512
37
+ mask_act: relu
38
+ n_blocks: 8
39
+ n_repeats: 3
40
+ n_src: 2
41
+ skip_chan: 128
42
+ optim:
43
+ lr: 0.001
44
+ optimizer: adam
45
+ weight_decay: 0.0
46
+ training:
47
+ batch_size: 6
48
+ early_stop: true
49
+ epochs: 200
50
+ half_lr: true
51
+ num_workers: 4
52
+ ```
53
+
54
+
55
+ Results:
56
+
57
+
58
+ On Libri2Mix min test set :
59
+ ```yml
60
+ 'si_sdr': 10.617130949793383,
61
+ 'si_sdr_imp': 12.551811412989263,
62
+ 'sdr': 11.231867464482065,
63
+ 'sdr_imp': 13.059765009747343,
64
+ 'sir': 24.461138352988346,
65
+ 'sir_imp': 24.371856452307703,
66
+ 'sar': 11.5649982725426,
67
+ 'sar_imp': 4.662525705768228,
68
+ 'stoi': 0.8701085138712695,
69
+ 'stoi_imp': 0.2245418019822898
70
+
71
+ ```
72
+
73
+
74
+ License notice:
75
+
76
+ This work "ConvTasNet_Libri2Mix_sepnoisy_16k" is a derivative of LibriSpeech ASR corpus by Vassil Panayotov,
77
+ used under CC BY 4.0; of The WSJ0 Hipster Ambient Mixtures
78
+ dataset by Whisper.ai, used under CC BY-NC 4.0 (Research only).
79
+ "ConvTasNet_Libri2Mix_sepnoisy_16k" is licensed under Attribution-ShareAlike 3.0 Unported by Joris Cosentino
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b685858ba025ecd25a14ca1117f9bd5f4ed806b03158da962b7ffabdc933c0
3
+ size 20394640