Initial commit
Browse files- README.md +77 -0
- pytorch_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- asteroid
|
| 4 |
+
- audio
|
| 5 |
+
- ConvTasNet
|
| 6 |
+
datasets:
|
| 7 |
+
- Libri3Mix
|
| 8 |
+
- sep_noisy
|
| 9 |
+
license: CC BY-NC 4.0
|
| 10 |
+
inference: false
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
## Asteroid model `JorisCos/ConvTasNet_Libri3Mix_sepnoisy_8k`
|
| 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 Libri3Mix dataset.
|
| 19 |
+
|
| 20 |
+
Training config:
|
| 21 |
+
|
| 22 |
+
```yml
|
| 23 |
+
data:
|
| 24 |
+
n_src: 3
|
| 25 |
+
sample_rate: 8000
|
| 26 |
+
segment: 3
|
| 27 |
+
task: sep_noisy
|
| 28 |
+
train_dir: data/wav8k/min/train-360
|
| 29 |
+
valid_dir: data/wav8k/min/dev
|
| 30 |
+
filterbank:
|
| 31 |
+
kernel_size: 16
|
| 32 |
+
n_filters: 512
|
| 33 |
+
stride: 8
|
| 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: 3
|
| 41 |
+
skip_chan: 128
|
| 42 |
+
optim:
|
| 43 |
+
lr: 0.001
|
| 44 |
+
optimizer: adam
|
| 45 |
+
weight_decay: 0.0
|
| 46 |
+
training:
|
| 47 |
+
batch_size: 24
|
| 48 |
+
early_stop: true
|
| 49 |
+
epochs: 200
|
| 50 |
+
half_lr: true
|
| 51 |
+
num_workers: 4
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
Results:
|
| 56 |
+
|
| 57 |
+
On Libri3Mix min test set :
|
| 58 |
+
```yml
|
| 59 |
+
'si_sdr': 5.978836560066222,
|
| 60 |
+
'si_sdr_imp': 10.388889689413096,
|
| 61 |
+
'sdr': 6.8651365291740225,
|
| 62 |
+
'sdr_imp': 10.928018056925016,
|
| 63 |
+
'sir': 14.997089638783114,
|
| 64 |
+
'sir_imp': 18.08248357801549,
|
| 65 |
+
'sar': 8.127504792061933,
|
| 66 |
+
'sar_imp': -0.7869320540959925,
|
| 67 |
+
'stoi': 0.7669414686111115,
|
| 68 |
+
'stoi_imp': 0.20416563213078837
|
| 69 |
+
```
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
License notice:
|
| 73 |
+
|
| 74 |
+
This work "ConvTasNet_Libri3Mix_sepnoisy_8k" is a derivative of LibriSpeech ASR corpus by Vassil Panayotov,
|
| 75 |
+
used under CC BY 4.0; of The WSJ0 Hipster Ambient Mixtures
|
| 76 |
+
dataset by Whisper.ai, used under CC BY-NC 4.0 (Research only).
|
| 77 |
+
"ConvTasNet_Libri3Mix_sepnoisy_8k" 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 sha256:8c0fcaf6d7d153467bafe4471b55db5e12d4a41083ee5cd1a59727a4c39ee7e2
|
| 3 |
+
size 20593552
|