|
--- |
|
tags: |
|
- asteroid |
|
- audio |
|
- MultiDecoderDPRNN |
|
datasets: |
|
- Wsj0MixVar |
|
- sep_clean |
|
inference: false |
|
--- |
|
## Asteroid model |
|
|
|
## Description: |
|
Refer to paper "Multi-Decoder DPRNN: High Accuracy Source Counting and Separation", |
|
Junzhe Zhu, Raymond Yeh, Mark Hasegawa-Johnson. https://arxiv.org/abs/2011.12022 |
|
Demo Page: https://junzhejosephzhu.github.io/Multi-Decoder-DPRNN/ |
|
Original research repo is at https://github.com/JunzheJosephZhu/MultiDecoder-DPRNN |
|
|
|
This model was trained by Joseph Zhu using the wsj0-mix-var/Multi-Decoder-DPRNN recipe in Asteroid. |
|
It was trained on the `sep_clean` task of the Wsj0MixVar dataset. |
|
|
|
## Training config: |
|
```yaml |
|
filterbank: |
|
n_filters: 64 |
|
kernel_size: 8 |
|
stride: 4 |
|
masknet: |
|
n_srcs: [2, 3, 4, 5] |
|
bn_chan: 128 |
|
hid_size: 128 |
|
chunk_size: 128 |
|
hop_size: 64 |
|
n_repeats: 8 |
|
mask_act: 'sigmoid' |
|
bidirectional: true |
|
dropout: 0 |
|
use_mulcat: false |
|
training: |
|
epochs: 200 |
|
batch_size: 2 |
|
num_workers: 2 |
|
half_lr: yes |
|
lr_decay: yes |
|
early_stop: yes |
|
gradient_clipping: 5 |
|
optim: |
|
optimizer: adam |
|
lr: 0.001 |
|
weight_decay: 0.00000 |
|
data: |
|
train_dir: "data/{}speakers/wav8k/min/tr" |
|
valid_dir: "data/{}speakers/wav8k/min/cv" |
|
task: sep_clean |
|
sample_rate: 8000 |
|
seglen: 4.0 |
|
minlen: 2.0 |
|
loss: |
|
lambda: 0.05 |
|
``` |
|
|
|
## Results: |
|
```yaml |
|
'Accuracy': 0.9723333333333334, 'P-Si-SNR': 10.36027378628496 |
|
``` |
|
|
