File size: 5,715 Bytes
4967734
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
config: conf/train_asr.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/asr_conformer_mono16k_warmup800_lr2e-4_accum2
ngpu: 1
seed: 0
num_workers: 1
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: null
dist_rank: null
local_rank: 0
dist_master_addr: null
dist_master_port: null
dist_launcher: null
multiprocessing_distributed: false
unused_parameters: false
sharded_ddp: false
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 250
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
-   - valid
    - acc
    - max
keep_nbest_models: 10
nbest_averaging_interval: 0
grad_clip: 5.0
grad_clip_type: 2.0
grad_noise: false
accum_grad: 2
no_forward_run: false
resume: true
train_dtype: float32
use_amp: false
log_interval: null
use_tensorboard: true
use_wandb: false
wandb_project: null
wandb_id: null
wandb_entity: null
wandb_name: null
wandb_model_log_interval: -1
detect_anomaly: false
pretrain_path: null
init_param: []
ignore_init_mismatch: false
freeze_param: []
num_iters_per_epoch: null
batch_size: 20
valid_batch_size: null
batch_bins: 2000000
valid_batch_bins: null
train_shape_file:
- exp/asr_stats_raw_word_sp/train/speech_shape
- exp/asr_stats_raw_word_sp/train/text_shape.word
valid_shape_file:
- exp/asr_stats_raw_word_sp/valid/speech_shape
- exp/asr_stats_raw_word_sp/valid/text_shape.word
batch_type: numel
valid_batch_type: null
fold_length:
- 80000
- 150
sort_in_batch: descending
sort_batch: descending
multiple_iterator: false
chunk_length: 500
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
train_data_path_and_name_and_type:
-   - dump/raw/train_sp/wav.scp
    - speech
    - sound
-   - dump/raw/train_sp/text
    - text
    - text
valid_data_path_and_name_and_type:
-   - dump/raw/dev/wav.scp
    - speech
    - sound
-   - dump/raw/dev/text
    - text
    - text
allow_variable_data_keys: false
max_cache_size: 0.0
max_cache_fd: 32
valid_max_cache_size: null
optim: adam
optim_conf:
    lr: 0.0002
scheduler: warmuplr
scheduler_conf:
    warmup_steps: 800
token_list:
- <blank>
- <unk>
- <move_rel-throttle="slow"-distance="little"-direction="backward"-/>
- <move_rel-throttle="slow"-distance="normal"-direction="backward"-/>
- <move_rel-throttle="slow"-distance="alot"-direction="backward"-/>
- <move_abs-throttle="fast"-pos_x="centerx"-pos_y="centery"-/>
- <move_abs-throttle="fast"-pos_x="left"-pos_y="up"-/>
- <move_abs-throttle="fast"-pos_x="right"-pos_y="down"-/>
- <move_abs-throttle="slow"-pos_x="centerx"-pos_y="centery"-/>
- <move_abs-throttle="slow"-pos_x="left"-pos_y="up"-/>
- <move_abs-throttle="slow"-pos_x="right"-pos_y="down"-/>
- <turn_rel-throttle="slow"-angle="south"-/>
- <move_rel-throttle="fast"-distance="little"-direction="forward"-/>
- <turn_rel-throttle="slow"-angle="east"-/>
- <turn_rel-throttle="slow"-angle="west"-/>
- <turn_rel-throttle="fast"-angle="south"-/>
- <turn_rel-throttle="fast"-angle="east"-/>
- <turn_rel-throttle="fast"-angle="west"-/>
- <turn_abs-angle="west"-/>
- <turn_abs-angle="east"-/>
- <turn_abs-angle="north"-/>
- <turn_abs-angle="south"-/>
- <lift-position="up"-/>
- <move_rel-throttle="fast"-distance="normal"-direction="forward"-/>
- <lift-position="down"-/>
- <approach-throttle="fast"-/>
- <approach-throttle="slow"-/>
- <grab-grabber="close"-/>
- <grab-grabber="open"-/>
- <pointer-state="off"-/>
- <pointer-state="on"-/>
- <move_rel-throttle="fast"-distance="alot"-direction="forward"-/>
- <move_rel-throttle="slow"-distance="little"-direction="forward"-/>
- <move_rel-throttle="slow"-distance="normal"-direction="forward"-/>
- <move_rel-throttle="slow"-distance="alot"-direction="forward"-/>
- <move_rel-throttle="fast"-distance="little"-direction="backward"-/>
- <move_rel-throttle="fast"-distance="normal"-direction="backward"-/>
- <move_rel-throttle="fast"-distance="alot"-direction="backward"-/>
- <sos/eos>
init: null
input_size: null
ctc_conf:
    dropout_rate: 0.0
    ctc_type: builtin
    reduce: true
    ignore_nan_grad: true
model_conf:
    ctc_weight: 0.0
    lsm_weight: 0.0
    length_normalized_loss: false
use_preprocessor: true
token_type: word
bpemodel: null
non_linguistic_symbols: null
cleaner: null
g2p: null
speech_volume_normalize: null
rir_scp: null
rir_apply_prob: 1.0
noise_scp: null
noise_apply_prob: 1.0
noise_db_range: '13_15'
frontend: default
frontend_conf:
    fs: 16000
specaug: specaug
specaug_conf:
    apply_time_warp: true
    time_warp_window: 5
    time_warp_mode: bicubic
    apply_freq_mask: true
    freq_mask_width_range:
    - 0
    - 30
    num_freq_mask: 2
    apply_time_mask: true
    time_mask_width_range:
    - 0
    - 40
    num_time_mask: 2
normalize: global_mvn
normalize_conf:
    stats_file: grabo/feats_stats.npz
preencoder: null
preencoder_conf: {}
encoder: conformer
encoder_conf:
    output_size: 256
    attention_heads: 4
    linear_units: 2048
    num_blocks: 12
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    attention_dropout_rate: 0.0
    input_layer: conv2d
    normalize_before: true
    macaron_style: true
    rel_pos_type: legacy
    pos_enc_layer_type: rel_pos
    selfattention_layer_type: rel_selfattn
    activation_type: swish
    use_cnn_module: true
    cnn_module_kernel: 15
postencoder: null
postencoder_conf: {}
decoder: transformer
decoder_conf:
    attention_heads: 4
    linear_units: 2048
    num_blocks: 6
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    self_attention_dropout_rate: 0.0
    src_attention_dropout_rate: 0.0
required:
- output_dir
- token_list
version: 0.10.5a1
distributed: false