1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
| # network architecture
| # encoder related
| encoder: eend_ola_transformer
| encoder_conf:
| idim: 345
| n_layers: 4
| n_units: 256
|
| # encoder-decoder attractor related
| encoder_decoder_attractor: eda
| encoder_decoder_attractor_conf:
| n_units: 256
|
| # model related
| model: eend_ola
| model_conf:
| max_n_speaker: 8
|
| # optimization related
| accum_grad: 1
| grad_clip: 5
| max_epoch: 25
| val_scheduler_criterion:
| - valid
| - loss
| best_model_criterion:
| - - valid
| - loss
| - min
| keep_nbest_models: 100
|
| optim: adam
| optim_conf:
| lr: 1.0
| betas:
| - 0.9
| - 0.98
| eps: 1.0e-9
| scheduler: noamlr
| scheduler_conf:
| model_size: 256
| warmup_steps: 100000
|
| dataset_conf:
| data_names: speech_speaker_labels
| data_types: kaldi_ark
| batch_conf:
| batch_type: unsorted
| batch_size: 64
| num_workers: 8
|
| log_interval: 50
|
|
