JorisCos commited on
Commit
514fcc7
1 Parent(s): d90998c

Initial commit

Browse files
Files changed (2) hide show
  1. README.md +82 -0
  2. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - asteroid
4
+ - audio
5
+ - ConvTasNet
6
+ datasets:
7
+ - Libri1Mix
8
+ - enh_single
9
+ license: CC BY-NC 4.0
10
+ inference: false
11
+ ---
12
+
13
+ ## Asteroid model `JorisCos/DPRNNTasNet_Libri1Mix_enhsignle_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 `enh_single` task of the Libri1Mix dataset.
19
+
20
+ Training config:
21
+
22
+ ```yml
23
+ data:
24
+ n_src: 1
25
+ sample_rate: 16000
26
+ segment: 1
27
+ task: enh_single
28
+ train_dir: data/wav16k/min/train-360
29
+ valid_dir: data/wav16k/min/dev
30
+ filterbank:
31
+ kernel_size: 2
32
+ n_filters: 64
33
+ stride: 1
34
+ masknet:
35
+ bidirectional: true
36
+ bn_chan: 128
37
+ chunk_size: 250
38
+ dropout: 0
39
+ hid_size: 128
40
+ hop_size: 125
41
+ in_chan: 64
42
+ mask_act: sigmoid
43
+ n_repeats: 6
44
+ n_src: 1
45
+ out_chan: 64
46
+ optim:
47
+ lr: 0.001
48
+ optimizer: adam
49
+ weight_decay: 1.0e-05
50
+ training:
51
+ batch_size: 2
52
+ early_stop: true
53
+ epochs: 200
54
+ gradient_clipping: 5
55
+ half_lr: true
56
+ num_workers: 4
57
+ ```
58
+
59
+
60
+ Results:
61
+
62
+ On Libri1Mix min test set :
63
+ ```yml
64
+ si_sdr: 14.7228101708889,
65
+ si_sdr_imp: 11.2730288650292,
66
+ sdr: 15.35661405197161,
67
+ sdr_imp: 11.853951252758595,
68
+ sir: Infinity,
69
+ sir_imp: NaN,
70
+ sar: 15.35661405197161,
71
+ sar_imp: 11.853951252758595,
72
+ stoi: 0.9300461826351578,
73
+ stoi_imp: 0.13412635909461715
74
+ ```
75
+
76
+
77
+ License notice:
78
+
79
+ This work "DPRNNTasNet_Libri1Mix_enhsignle_16k" is a derivative of [LibriSpeech ASR corpus](http://www.openslr.org/12) by Vassil Panayotov,
80
+ used under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); of The WSJ0 Hipster Ambient Mixtures
81
+ dataset by [Whisper.ai](http://wham.whisper.ai/), used under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) (Research only).
82
+ "DPRNNTasNet_Libri1Mix_enhsignle_16k" 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 sha256:6b510c07fae3a3db18473b5749316cb9df8dc4f78164c3cdfbb50d3783ee779d
3
+ size 14595773