JorisCos commited on
Commit
e5ac721
1 Parent(s): 7e10ba9

add model and readme

Browse files
Files changed (2) hide show
  1. README.md +71 -0
  2. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - asteroid
4
+ - audio
5
+ - VADNet
6
+ - VAD
7
+ - Voice Activity Detection
8
+ datasets:
9
+ - LibriVAD
10
+ license: cc-by-sa-4.0
11
+ ---
12
+
13
+ ## Asteroid model `JorisCos/VAD_Net`
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 `enh_single` task of the Libri1Mix dataset.
19
+
20
+ Training config:
21
+
22
+ ```yml
23
+ data:
24
+ segment: 3
25
+ train_dir: /home/jcosentino/VAD_dataset/metadata/sets/train.json
26
+ valid_dir: /home/jcosentino/VAD_dataset/metadata/sets/dev.json
27
+ filterbank:
28
+ kernel_size: 16
29
+ n_filters: 512
30
+ stride: 8
31
+ main_args:
32
+ exp_dir: exp/full_not_causal_f1/
33
+ help: null
34
+ masknet:
35
+ bn_chan: 128
36
+ causal: false
37
+ hid_chan: 512
38
+ mask_act: relu
39
+ n_blocks: 3
40
+ n_repeats: 5
41
+ skip_chan: 128
42
+ optim:
43
+ lr: 0.001
44
+ optimizer: adam
45
+ weight_decay: 0.0
46
+ positional arguments: {}
47
+ training:
48
+ batch_size: 8
49
+ early_stop: true
50
+ epochs: 200
51
+ half_lr: true
52
+ num_workers: 4
53
+ ```
54
+
55
+
56
+ Results:
57
+
58
+ On LibriVAD min test set :
59
+ ```yml
60
+ accuracy: 0.8196149023502931,
61
+ precision: 0.8305009048356607,
62
+ recall: 0.8869202491310206,
63
+ f1_score: 0.8426184545700124
64
+ ```
65
+
66
+
67
+ License notice:
68
+
69
+ This work "VAD_Net" is a derivative of [LibriSpeech ASR corpus](http://www.openslr.org/12) by Vassil Panayotov,
70
+ used under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); of The [DNS challenge](https://github.com/microsoft/DNS-Challenge) noises, [Attribution-ShareAlike 3.0 Unported](https://creativecommons.org/licenses/by-sa/3.0/).
71
+ "VAD_Net" is licensed under [Attribution-ShareAlike 3.0 Unported](https://creativecommons.org/licenses/by-sa/3.0/) by Joris Cosentino
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa7cc10c60e2bc94708ac9d8ec546baea1bb466738bb89adc89844d07a4e242
3
+ size 12765410