-
Notifications
You must be signed in to change notification settings - Fork 0
/
TIMIT_LSTMP_mfcc.cfg
209 lines (190 loc) · 5.61 KB
/
TIMIT_LSTMP_mfcc.cfg
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
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
[cfg_proto]
cfg_proto = proto/global.proto
cfg_proto_chunk = proto/global_chunk.proto
[exp]
cmd =
run_nn_script = run_nn
out_folder = exp/TIMIT_LSTMP_mfcc_T
seed = 2234
use_cuda = True
multi_gpu = False
save_gpumem = False
n_epochs_tr = 24
[dataset1]
data_name = TIMIT_tr
fea = fea_name=mfcc
fea_lst=/home/mingju/kaldi/egs/timit/s5/data/train/feats.scp
fea_opts=apply-cmvn --utt2spk=ark:/home/mingju/kaldi/egs/timit/s5/data/train/utt2spk ark:/home/mingju/kaldi/egs/timit/s5/mfcc/cmvn_train.ark ark:- ark:- | add-deltas --delta-order=2 ark:- ark:- |
cw_left=0
cw_right=0
lab = lab_name=lab_cd
lab_folder=/home/mingju/kaldi/egs/timit/s5/exp/dnn4_pretrain-dbn_dnn_ali
lab_opts=ali-to-pdf
lab_count_file=auto
lab_data_folder=/home/mingju/kaldi/egs/timit/s5/data/train/
lab_graph=/home/mingju/kaldi/egs/timit/s5/exp/tri3/graph
lab_name=lab_mono
lab_folder=/home/mingju/kaldi/egs/timit/s5/exp/dnn4_pretrain-dbn_dnn_ali
lab_opts=ali-to-phones --per-frame=true
lab_count_file=none
lab_data_folder=/home/mingju/kaldi/egs/timit/s5/data/train/
lab_graph=/home/mingju/kaldi/egs/timit/s5/exp/mono/graph
n_chunks = 5
[dataset2]
data_name = TIMIT_dev
fea = fea_name=mfcc
fea_lst=/home/mingju/kaldi/egs/timit/s5/data/dev/feats.scp
fea_opts=apply-cmvn --utt2spk=ark:/home/mingju/kaldi/egs/timit/s5/data/dev/utt2spk ark:/home/mingju/kaldi/egs/timit/s5/mfcc/cmvn_dev.ark ark:- ark:- | add-deltas --delta-order=2 ark:- ark:- |
cw_left=0
cw_right=0
lab = lab_name=lab_cd
lab_folder=/home/mingju/kaldi/egs/timit/s5/exp/dnn4_pretrain-dbn_dnn_ali_dev
lab_opts=ali-to-pdf
lab_count_file=auto
lab_data_folder=/home/mingju/kaldi/egs/timit/s5/data/dev/
lab_graph=/home/mingju/kaldi/egs/timit/s5/exp/tri3/graph
lab_name=lab_mono
lab_folder=/home/mingju/kaldi/egs/timit/s5/exp/dnn4_pretrain-dbn_dnn_ali_dev
lab_opts=ali-to-phones --per-frame=true
lab_count_file=none
lab_data_folder=/home/mingju/kaldi/egs/timit/s5/data/dev/
lab_graph=/home/mingju/kaldi/egs/timit/s5/exp/mono/graph
n_chunks = 1
[dataset3]
data_name = TIMIT_test
fea = fea_name=mfcc
fea_lst=/home/mingju/kaldi/egs/timit/s5/data/test/feats.scp
fea_opts=apply-cmvn --utt2spk=ark:/home/mingju/kaldi/egs/timit/s5/data/test/utt2spk ark:/home/mingju/kaldi/egs/timit/s5/mfcc/cmvn_test.ark ark:- ark:- | add-deltas --delta-order=2 ark:- ark:- |
cw_left=0
cw_right=0
lab = lab_name=lab_cd
lab_folder=/home/mingju/kaldi/egs/timit/s5/exp/dnn4_pretrain-dbn_dnn_ali_test
lab_opts=ali-to-pdf
lab_count_file=auto
lab_data_folder=/home/mingju/kaldi/egs/timit/s5/data/test/
lab_graph=/home/mingju/kaldi/egs/timit/s5/exp/tri3/graph
lab_name=lab_mono
lab_folder=/home/mingju/kaldi/egs/timit/s5/exp/dnn4_pretrain-dbn_dnn_ali_test
lab_opts=ali-to-phones --per-frame=true
lab_count_file=none
lab_data_folder=/home/mingju/kaldi/egs/timit/s5/data/test/
lab_graph=/home/mingju/kaldi/egs/timit/s5/exp/mono/graph
n_chunks = 1
[data_use]
train_with = TIMIT_tr
valid_with = TIMIT_dev
forward_with = TIMIT_test
[batches]
batch_size_train = 8
max_seq_length_train = 1000
increase_seq_length_train = True
start_seq_len_train = 100
multply_factor_seq_len_train = 2
batch_size_valid = 8
max_seq_length_valid = 1000
[architecture1]
arch_name = LSTMP_layers
arch_proto = proto/LSTMP.proto
arch_library = neural_networks
arch_class = LSTMP
arch_pretrain_file = none
arch_freeze = False
arch_seq_model = True
lstm_lay = 1024,1024
proj_lay = 512,512
lstm_drop = 0.2,0.2
lstm_use_laynorm_inp = False
lstm_use_batchnorm_inp = False
lstm_use_laynorm = False,False
lstm_use_batchnorm = True,True
lstm_bidir = False
lstm_act = tanh,tanh
lstm_orthinit = True
arch_lr = 0.0004
arch_halving_factor = 0.5
arch_improvement_threshold = 0.001
arch_opt = rmsprop
opt_momentum = 0.0
opt_alpha = 0.95
opt_eps = 1e-8
opt_centered = False
opt_weight_decay = 0.0
[architecture2]
arch_name = MLP_layers
arch_proto = proto/MLP.proto
arch_library = neural_networks
arch_class = MLP
arch_pretrain_file = none
arch_freeze = False
arch_seq_model = False
dnn_lay = N_out_lab_cd
dnn_drop = 0.0
dnn_use_laynorm_inp = False
dnn_use_batchnorm_inp = False
dnn_use_batchnorm = False
dnn_use_laynorm = False
dnn_act = softmax
arch_lr = 0.0016
arch_halving_factor = 0.5
arch_improvement_threshold = 0.001
arch_opt = rmsprop
opt_momentum = 0.0
opt_alpha = 0.95
opt_eps = 1e-8
opt_centered = False
opt_weight_decay = 0.0
[architecture3]
arch_name = MLP_layers2
arch_proto = proto/MLP.proto
arch_library = neural_networks
arch_class = MLP
arch_pretrain_file = none
arch_freeze = False
arch_seq_model = False
dnn_lay = N_out_lab_mono
dnn_drop = 0.0
dnn_use_laynorm_inp = False
dnn_use_batchnorm_inp = False
dnn_use_batchnorm = False
dnn_use_laynorm = False
dnn_act = softmax
arch_lr = 0.0004
arch_halving_factor = 0.5
arch_improvement_threshold = 0.001
arch_opt = rmsprop
opt_momentum = 0.0
opt_alpha = 0.95
opt_eps = 1e-8
opt_centered = False
opt_weight_decay = 0.0
[model]
model_proto = proto/model.proto
model = out_dnn1=compute(LSTMP_layers,mfcc)
out_dnn2=compute(MLP_layers,out_dnn1)
out_dnn3=compute(MLP_layers2,out_dnn1)
loss_mono=cost_nll(out_dnn3,lab_mono)
loss_mono_w=mult_constant(loss_mono,1.0)
loss_cd=cost_nll(out_dnn2,lab_cd)
loss_final=sum(loss_cd,loss_mono_w)
err_final=cost_err(out_dnn2,lab_cd)
[forward]
forward_out = out_dnn2
normalize_posteriors = True
normalize_with_counts_from = lab_cd
save_out_file = False
require_decoding = True
[decoding]
decoding_script_folder = kaldi_decoding_scripts/
decoding_script = decode_dnn.sh
decoding_proto = proto/decoding.proto
min_active = 200
max_active = 7000
max_mem = 50000000
beam = 13.0
latbeam = 8.0
acwt = 0.2
max_arcs = -1
skip_scoring = false
scoring_script = local/score.sh
scoring_opts = "--min-lmwt 1 --max-lmwt 10"
norm_vars = False