Hugging Face's logo

soumi-maiti
/
speech-ulm-lstm

Model card Files Community
soumi-maiti commited on
Commit
908f278
•
1 Parent(s): fda340c

Update model

Browse files
Files changed (12) hide show
  1. config.yaml +176 -0
  2. images/backward_time.png +0 -0
  3. images/forward_time.png +0 -0
  4. images/gpu_max_cached_mem_GB.png +0 -0
  5. images/iter_time.png +0 -0
  6. images/loss.png +0 -0
  7. images/optim0_lr0.png +0 -0
  8. images/optim_step_time.png +0 -0
  9. images/train_time.png +0 -0
  10. tokens.txt +53 -0
  11. valid.loss.ave.pth +3 -0
  12. valid.loss.best.pth +3 -0
config.yaml ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config: conf/train_lm_rnn_unit1024_nlayers3_dropout0.2.yaml
2
+ print_config: false
3
+ log_level: INFO
4
+ dry_run: false
5
+ iterator_type: sequence
6
+ output_dir: exp/lm_train_lm_rnn_unit1024_nlayers3_dropout0.2_word
7
+ ngpu: 1
8
+ seed: 0
9
+ num_workers: 1
10
+ num_att_plot: 3
11
+ dist_backend: nccl
12
+ dist_init_method: env://
13
+ dist_world_size: 2
14
+ dist_rank: 0
15
+ local_rank: 0
16
+ dist_master_addr: localhost
17
+ dist_master_port: 35485
18
+ dist_launcher: null
19
+ multiprocessing_distributed: true
20
+ unused_parameters: false
21
+ sharded_ddp: false
22
+ cudnn_enabled: true
23
+ cudnn_benchmark: false
24
+ cudnn_deterministic: true
25
+ collect_stats: false
26
+ write_collected_feats: false
27
+ max_epoch: 40
28
+ patience: null
29
+ val_scheduler_criterion:
30
+ - valid
31
+ - loss
32
+ early_stopping_criterion:
33
+ - valid
34
+ - loss
35
+ - min
36
+ best_model_criterion:
37
+ - - valid
38
+ - loss
39
+ - min
40
+ keep_nbest_models: 1
41
+ nbest_averaging_interval: 0
42
+ grad_clip: 5.0
43
+ grad_clip_type: 2.0
44
+ grad_noise: false
45
+ accum_grad: 1
46
+ no_forward_run: false
47
+ resume: true
48
+ train_dtype: float32
49
+ use_amp: true
50
+ log_interval: null
51
+ use_matplotlib: true
52
+ use_tensorboard: true
53
+ create_graph_in_tensorboard: false
54
+ use_wandb: false
55
+ wandb_project: null
56
+ wandb_id: null
57
+ wandb_entity: null
58
+ wandb_name: null
59
+ wandb_model_log_interval: -1
60
+ detect_anomaly: false
61
+ pretrain_path: null
62
+ init_param: []
63
+ ignore_init_mismatch: false
64
+ freeze_param: []
65
+ num_iters_per_epoch: null
66
+ batch_size: 20
67
+ valid_batch_size: null
68
+ batch_bins: 10000000
69
+ valid_batch_bins: null
70
+ train_shape_file:
71
+ - exp/lm_stats_word/train/text_shape.word
72
+ valid_shape_file:
73
+ - exp/lm_stats_word/valid/text_shape.word
74
+ batch_type: numel
75
+ valid_batch_type: null
76
+ fold_length:
77
+ - 150
78
+ sort_in_batch: descending
79
+ sort_batch: descending
80
+ multiple_iterator: false
81
+ chunk_length: 500
82
+ chunk_shift_ratio: 0.5
83
+ num_cache_chunks: 1024
84
+ train_data_path_and_name_and_type:
85
+ - - dump/raw/lm_train.txt
86
+ - text
87
+ - text
88
+ valid_data_path_and_name_and_type:
89
+ - - nunit_50_rep/lm_valid_50_rep.txt
90
+ - text
91
+ - text
92
+ allow_variable_data_keys: false
93
+ max_cache_size: 0.0
94
+ max_cache_fd: 32
95
+ valid_max_cache_size: null
96
+ optim: adam
97
+ optim_conf:
98
+ lr: 0.002
99
+ scheduler: reducelronplateau
100
+ scheduler_conf:
101
+ mode: min
102
+ factor: 0.5
103
+ patience: 2
104
+ token_list:
105
+ - <blank>
106
+ - <unk>
107
+ - '7'
108
+ - '35'
109
+ - '44'
110
+ - '49'
111
+ - '20'
112
+ - '47'
113
+ - '0'
114
+ - '3'
115
+ - '46'
116
+ - '45'
117
+ - '31'
118
+ - '11'
119
+ - '28'
120
+ - '4'
121
+ - '37'
122
+ - '43'
123
+ - '26'
124
+ - '36'
125
+ - '18'
126
+ - '32'
127
+ - '5'
128
+ - '14'
129
+ - '33'
130
+ - '16'
131
+ - '9'
132
+ - '8'
133
+ - '17'
134
+ - '30'
135
+ - '24'
136
+ - '48'
137
+ - '21'
138
+ - '34'
139
+ - '6'
140
+ - '29'
141
+ - '38'
142
+ - '23'
143
+ - '39'
144
+ - '10'
145
+ - '27'
146
+ - '19'
147
+ - '40'
148
+ - '42'
149
+ - '25'
150
+ - '41'
151
+ - '12'
152
+ - '15'
153
+ - '1'
154
+ - '2'
155
+ - '13'
156
+ - '22'
157
+ - <sos/eos>
158
+ init: null
159
+ model_conf:
160
+ ignore_id: 0
161
+ use_preprocessor: true
162
+ token_type: word
163
+ bpemodel: null
164
+ non_linguistic_symbols: null
165
+ cleaner: null
166
+ g2p: null
167
+ lm: seq_rnn
168
+ lm_conf:
169
+ unit: 1024
170
+ nlayers: 3
171
+ dropout_rate: 0.2
172
+ required:
173
+ - output_dir
174
+ - token_list
175
+ version: '202207'
176
+ distributed: true
images/backward_time.png ADDED
images/forward_time.png ADDED
images/gpu_max_cached_mem_GB.png ADDED
images/iter_time.png ADDED
images/loss.png ADDED
images/optim0_lr0.png ADDED
images/optim_step_time.png ADDED
images/train_time.png ADDED
tokens.txt ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <blank>
2
+ <unk>
3
+ 7
4
+ 35
5
+ 44
6
+ 49
7
+ 20
8
+ 47
9
+ 0
10
+ 3
11
+ 46
12
+ 45
13
+ 31
14
+ 11
15
+ 28
16
+ 4
17
+ 37
18
+ 43
19
+ 26
20
+ 36
21
+ 18
22
+ 32
23
+ 5
24
+ 14
25
+ 33
26
+ 16
27
+ 9
28
+ 8
29
+ 17
30
+ 30
31
+ 24
32
+ 48
33
+ 21
34
+ 34
35
+ 6
36
+ 29
37
+ 38
38
+ 23
39
+ 39
40
+ 10
41
+ 27
42
+ 19
43
+ 40
44
+ 42
45
+ 25
46
+ 41
47
+ 12
48
+ 15
49
+ 1
50
+ 2
51
+ 13
52
+ 22
53
+ <sos/eos>
valid.loss.ave.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff751697701ba255d73e6bd0446a9553c941c45525dba8b64a6abcb1f1f8d9c
3
+ size 101198559
valid.loss.best.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff751697701ba255d73e6bd0446a9553c941c45525dba8b64a6abcb1f1f8d9c
3
+ size 101198559