prekshaupatel commited on
Commit
2833cba
1 Parent(s): 6bb1687

Add model files

Browse files
Files changed (29) hide show
  1. exp/asr_stats_raw_ml_bpe150_sp/train/feats_lengths_stats.npz +0 -0
  2. exp/asr_stats_raw_ml_bpe150_sp/train/feats_stats.npz +0 -0
  3. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/RESULTS.md +32 -0
  4. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/config.yaml +348 -0
  5. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/acc.png +0 -0
  6. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/backward_time.png +0 -0
  7. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/cer.png +0 -0
  8. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/cer_ctc.png +0 -0
  9. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/forward_time.png +0 -0
  10. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/gpu_max_cached_mem_GB.png +0 -0
  11. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/iter_time.png +0 -0
  12. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/loss.png +0 -0
  13. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/loss_att.png +0 -0
  14. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/loss_ctc.png +0 -0
  15. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/optim0_lr0.png +0 -0
  16. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/optim_step_time.png +0 -0
  17. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/train_time.png +0 -0
  18. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/wer.png +0 -0
  19. exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/valid.acc.ave_10best.pth +3 -0
  20. exp/lm_train_lm_ml_bpe150/config.yaml +267 -0
  21. exp/lm_train_lm_ml_bpe150/images/backward_time.png +0 -0
  22. exp/lm_train_lm_ml_bpe150/images/forward_time.png +0 -0
  23. exp/lm_train_lm_ml_bpe150/images/gpu_max_cached_mem_GB.png +0 -0
  24. exp/lm_train_lm_ml_bpe150/images/iter_time.png +0 -0
  25. exp/lm_train_lm_ml_bpe150/images/loss.png +0 -0
  26. exp/lm_train_lm_ml_bpe150/images/optim0_lr0.png +0 -0
  27. exp/lm_train_lm_ml_bpe150/images/optim_step_time.png +0 -0
  28. exp/lm_train_lm_ml_bpe150/images/train_time.png +0 -0
  29. exp/lm_train_lm_ml_bpe150/valid.loss.ave_1best.pth +1 -0
exp/asr_stats_raw_ml_bpe150_sp/train/feats_lengths_stats.npz ADDED
Binary file (778 Bytes). View file
 
exp/asr_stats_raw_ml_bpe150_sp/train/feats_stats.npz ADDED
Binary file (1.4 kB). View file
 
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/RESULTS.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!-- Generated by scripts/utils/show_asr_result.sh -->
2
+ # RESULTS
3
+ ## Environments
4
+ - date: `Sat Mar 19 20:34:49 UTC 2022`
5
+ - python version: `3.9.10 | packaged by conda-forge | (main, Feb 1 2022, 21:24:11) [GCC 9.4.0]`
6
+ - espnet version: `espnet 0.10.7a1`
7
+ - pytorch version: `pytorch 1.10.1`
8
+ - Git hash: `d2410457152872f63c51ee76ed746a6ea3153f09`
9
+ - Commit date: `Sat Mar 19 09:04:54 2022 +0000`
10
+
11
+ ## asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp
12
+ ### WER
13
+
14
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
15
+ |---|---|---|---|---|---|---|---|---|
16
+ |decode_asr_lm_lm_train_lm_ml_bpe150_valid.loss.ave_asr_model_valid.acc.ave/dev_ml|369|2345|75.2|21.8|3.0|2.4|27.2|71.5|
17
+ |decode_asr_lm_lm_train_lm_ml_bpe150_valid.loss.ave_asr_model_valid.acc.ave/test_ml|1062|6136|67.0|28.7|4.3|2.6|35.6|71.8|
18
+
19
+ ### CER
20
+
21
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
22
+ |---|---|---|---|---|---|---|---|---|
23
+ |decode_asr_lm_lm_train_lm_ml_bpe150_valid.loss.ave_asr_model_valid.acc.ave/dev_ml|369|21321|96.1|2.2|1.7|0.9|4.7|71.5|
24
+ |decode_asr_lm_lm_train_lm_ml_bpe150_valid.loss.ave_asr_model_valid.acc.ave/test_ml|1062|57065|93.5|3.2|3.3|1.3|7.7|71.8|
25
+
26
+ ### TER
27
+
28
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
29
+ |---|---|---|---|---|---|---|---|---|
30
+ |decode_asr_lm_lm_train_lm_ml_bpe150_valid.loss.ave_asr_model_valid.acc.ave/dev_ml|369|13402|93.5|4.4|2.1|0.9|7.4|71.3|
31
+ |decode_asr_lm_lm_train_lm_ml_bpe150_valid.loss.ave_asr_model_valid.acc.ave/test_ml|1062|35911|89.9|6.3|3.8|1.3|11.4|70.4|
32
+
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/config.yaml ADDED
@@ -0,0 +1,348 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config: conf/tuning/train_asr_conformer_s3prlfrontend_hubert_fused.yaml
2
+ print_config: false
3
+ log_level: INFO
4
+ dry_run: false
5
+ iterator_type: sequence
6
+ output_dir: exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp
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: null
14
+ dist_rank: null
15
+ local_rank: 0
16
+ dist_master_addr: null
17
+ dist_master_port: null
18
+ dist_launcher: null
19
+ multiprocessing_distributed: false
20
+ unused_parameters: false
21
+ sharded_ddp: false
22
+ cudnn_enabled: true
23
+ cudnn_benchmark: false
24
+ cudnn_deterministic: false
25
+ collect_stats: false
26
+ write_collected_feats: false
27
+ max_epoch: 50
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
+ - acc
39
+ - max
40
+ keep_nbest_models: 10
41
+ nbest_averaging_interval: 0
42
+ grad_clip: 3
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
+ use_wandb: false
54
+ wandb_project: null
55
+ wandb_id: null
56
+ wandb_entity: null
57
+ wandb_name: null
58
+ wandb_model_log_interval: -1
59
+ detect_anomaly: false
60
+ pretrain_path: null
61
+ init_param: []
62
+ ignore_init_mismatch: false
63
+ freeze_param: []
64
+ num_iters_per_epoch: null
65
+ batch_size: 20
66
+ valid_batch_size: null
67
+ batch_bins: 2000000
68
+ valid_batch_bins: null
69
+ train_shape_file:
70
+ - exp/asr_stats_raw_ml_bpe150_sp/train/speech_shape
71
+ - exp/asr_stats_raw_ml_bpe150_sp/train/text_shape.bpe
72
+ valid_shape_file:
73
+ - exp/asr_stats_raw_ml_bpe150_sp/valid/speech_shape
74
+ - exp/asr_stats_raw_ml_bpe150_sp/valid/text_shape.bpe
75
+ batch_type: numel
76
+ valid_batch_type: null
77
+ fold_length:
78
+ - 80000
79
+ - 150
80
+ sort_in_batch: descending
81
+ sort_batch: descending
82
+ multiple_iterator: false
83
+ chunk_length: 500
84
+ chunk_shift_ratio: 0.5
85
+ num_cache_chunks: 1024
86
+ train_data_path_and_name_and_type:
87
+ - - dump/raw/train_ml_sp/wav.scp
88
+ - speech
89
+ - sound
90
+ - - dump/raw/train_ml_sp/text
91
+ - text
92
+ - text
93
+ valid_data_path_and_name_and_type:
94
+ - - dump/raw/dev_ml/wav.scp
95
+ - speech
96
+ - sound
97
+ - - dump/raw/dev_ml/text
98
+ - text
99
+ - text
100
+ allow_variable_data_keys: false
101
+ max_cache_size: 0.0
102
+ max_cache_fd: 32
103
+ valid_max_cache_size: null
104
+ optim: adam
105
+ optim_conf:
106
+ lr: 0.5
107
+ scheduler: noamlr
108
+ scheduler_conf:
109
+ warmup_steps: 2500
110
+ token_list:
111
+ - <blank>
112
+ - <unk>
113
+ - ്
114
+ - ാ
115
+ - ി
116
+ - ു
117
+ - ര
118
+ - ▁
119
+ - ം
120
+ - യ
121
+ - ല
122
+ - െ
123
+ - വ
124
+ - ക
125
+ - ത
126
+ - ക്ക
127
+ - ▁അ
128
+ - ന
129
+ - ട
130
+ - മ
131
+ - േ
132
+ - ോ
133
+ - റ
134
+ - ▁പ
135
+ - ർ
136
+ - ണ
137
+ - ▁ക
138
+ - ▁സ
139
+ - ▁മ
140
+ - ത്ത
141
+ - ള
142
+ - ദ
143
+ - ▁വ
144
+ - ും
145
+ - ▁ആ
146
+ - ന്ന
147
+ - സ
148
+ - ത്
149
+ - ീ
150
+ - ▁ത
151
+ - പ
152
+ - ▁ന
153
+ - ന്
154
+ - ൂ
155
+ - ശ
156
+ - ട്ട
157
+ - ിയ
158
+ - ൻ
159
+ - ഗ
160
+ - ‍
161
+ - ▁എന്ന
162
+ - പ്പ
163
+ - തി
164
+ - സ്
165
+ - ്യ
166
+ - ▁ഇ
167
+ - ൽ
168
+ - ങ്ങ
169
+ - റ്റ
170
+ - ുന്ന
171
+ - ഭ
172
+ - ാണ്
173
+ - രി
174
+ - ഹ
175
+ - ണ്ട
176
+ - ത്തി
177
+ - ▁അവ
178
+ - ധ
179
+ - ഷ
180
+ - ▁എ
181
+ - ാന
182
+ - ▁ച
183
+ - ത്ര
184
+ - ▁പ്ര
185
+ - ായി
186
+ - ▁നി
187
+ - മായ
188
+ - ിൽ
189
+ - ▁ഒരു
190
+ - ഥ
191
+ - കള
192
+ - ▁വി
193
+ - ജ
194
+ - ിന്റെ
195
+ - ബ
196
+ - ക്കുന്ന
197
+ - ിച്ച
198
+ - ങ്ങൾ
199
+ - ▁കാ
200
+ - ുണ്ട
201
+ - ുള്ള
202
+ - ായിരുന്നു
203
+ - ച
204
+ - ക്ഷ
205
+ - കൾ
206
+ - ിരുന്ന
207
+ - ല്ല
208
+ - ൾ
209
+ - യും
210
+ - ▁ജ
211
+ - ▁ബ
212
+ - ഡ
213
+ - ച്ച
214
+ - ▁അതിന
215
+ - ുടെ
216
+ - ിച്ചു
217
+ - ൈ
218
+ - ില്ല
219
+ - ▁ശ
220
+ - യിൽ
221
+ - മാണ്
222
+ - യുടെ
223
+ - ത്തിൽ
224
+ - ൃ
225
+ - ഫ
226
+ - ഖ
227
+ - ഠ
228
+ - e
229
+ - ൺ
230
+ - ഘ
231
+ - _
232
+ - '-'
233
+ - ഐ
234
+ - എ
235
+ - n
236
+ - ൌ
237
+ - ഃ
238
+ - അ
239
+ - ഔ
240
+ - ഊ
241
+ - ഛ
242
+ - r
243
+ - l
244
+ - t
245
+ - ഓ
246
+ - ൗ
247
+ - ഏ
248
+ - ഈ
249
+ - ഉ
250
+ - ൊ
251
+ - ഴ
252
+ - ഞ
253
+ - ഒ
254
+ - ഇ
255
+ - ആ
256
+ - ഋ
257
+ - ഝ
258
+ - ങ
259
+ - ഢ
260
+ - <sos/eos>
261
+ init: null
262
+ input_size: null
263
+ ctc_conf:
264
+ dropout_rate: 0.0
265
+ ctc_type: builtin
266
+ reduce: true
267
+ ignore_nan_grad: true
268
+ joint_net_conf: null
269
+ model_conf:
270
+ ctc_weight: 0.3
271
+ lsm_weight: 0.1
272
+ length_normalized_loss: false
273
+ use_preprocessor: true
274
+ token_type: bpe
275
+ bpemodel: data/ml_token_list/bpe_unigram150/bpe.model
276
+ non_linguistic_symbols: null
277
+ cleaner: null
278
+ g2p: null
279
+ speech_volume_normalize: null
280
+ rir_scp: null
281
+ rir_apply_prob: 1.0
282
+ noise_scp: null
283
+ noise_apply_prob: 1.0
284
+ noise_db_range: '13_15'
285
+ frontend: fused
286
+ frontend_conf:
287
+ frontends:
288
+ - frontend_type: s3prl
289
+ frontend_conf:
290
+ upstream: hubert_large_ll60k
291
+ download_dir: ./hub
292
+ multilayer_feature: true
293
+ - frontend_type: default
294
+ n_fft: 512
295
+ win_length: 400
296
+ hop_length: 160
297
+ align_method: linear_projection
298
+ proj_dim: 100
299
+ fs: 16k
300
+ specaug: specaug
301
+ specaug_conf:
302
+ apply_time_warp: true
303
+ time_warp_window: 5
304
+ time_warp_mode: bicubic
305
+ apply_freq_mask: true
306
+ freq_mask_width_range:
307
+ - 0
308
+ - 30
309
+ num_freq_mask: 2
310
+ apply_time_mask: true
311
+ time_mask_width_range:
312
+ - 0
313
+ - 40
314
+ num_time_mask: 2
315
+ normalize: utterance_mvn
316
+ normalize_conf: {}
317
+ preencoder: linear
318
+ preencoder_conf:
319
+ input_size: 200
320
+ output_size: 80
321
+ encoder: conformer
322
+ encoder_conf:
323
+ input_layer: conv2d
324
+ num_blocks: 12
325
+ linear_units: 2048
326
+ dropout_rate: 0.1
327
+ output_size: 256
328
+ attention_heads: 4
329
+ attention_dropout_rate: 0.0
330
+ pos_enc_layer_type: rel_pos
331
+ selfattention_layer_type: rel_selfattn
332
+ activation_type: swish
333
+ macaron_style: true
334
+ use_cnn_module: true
335
+ cnn_module_kernel: 15
336
+ postencoder: null
337
+ postencoder_conf: {}
338
+ decoder: transformer
339
+ decoder_conf:
340
+ input_layer: embed
341
+ num_blocks: 6
342
+ linear_units: 2048
343
+ dropout_rate: 0.1
344
+ required:
345
+ - output_dir
346
+ - token_list
347
+ version: 0.10.7a1
348
+ distributed: false
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/acc.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/backward_time.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/cer.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/cer_ctc.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/forward_time.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/gpu_max_cached_mem_GB.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/iter_time.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/loss.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/loss_att.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/loss_ctc.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/optim0_lr0.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/optim_step_time.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/train_time.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/images/wer.png ADDED
exp/asr_train_asr_conformer_s3prlfrontend_hubert_fused_raw_ml_bpe150_sp/valid.acc.ave_10best.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c446bbc1dbcf517f45d633657575dd052e1735e83fabe8f61e28c989d9c9b092
3
+ size 1440097508
exp/lm_train_lm_ml_bpe150/config.yaml ADDED
@@ -0,0 +1,267 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config: conf/train_lm.yaml
2
+ print_config: false
3
+ log_level: INFO
4
+ dry_run: false
5
+ iterator_type: sequence
6
+ output_dir: exp/lm_train_lm_ml_bpe150
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: null
14
+ dist_rank: null
15
+ local_rank: 0
16
+ dist_master_addr: null
17
+ dist_master_port: null
18
+ dist_launcher: null
19
+ multiprocessing_distributed: false
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: 30
28
+ patience: 3
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: false
50
+ log_interval: null
51
+ use_matplotlib: true
52
+ use_tensorboard: true
53
+ use_wandb: false
54
+ wandb_project: null
55
+ wandb_id: null
56
+ wandb_entity: null
57
+ wandb_name: null
58
+ wandb_model_log_interval: -1
59
+ detect_anomaly: false
60
+ pretrain_path: null
61
+ init_param: []
62
+ ignore_init_mismatch: false
63
+ freeze_param: []
64
+ num_iters_per_epoch: null
65
+ batch_size: 64
66
+ valid_batch_size: null
67
+ batch_bins: 1000000
68
+ valid_batch_bins: null
69
+ train_shape_file:
70
+ - exp/lm_stats_ml_bpe150/train/text_shape.bpe
71
+ valid_shape_file:
72
+ - exp/lm_stats_ml_bpe150/valid/text_shape.bpe
73
+ batch_type: folded
74
+ valid_batch_type: null
75
+ fold_length:
76
+ - 150
77
+ sort_in_batch: descending
78
+ sort_batch: descending
79
+ multiple_iterator: false
80
+ chunk_length: 500
81
+ chunk_shift_ratio: 0.5
82
+ num_cache_chunks: 1024
83
+ train_data_path_and_name_and_type:
84
+ - - dump/raw/lm_train.txt
85
+ - text
86
+ - text
87
+ valid_data_path_and_name_and_type:
88
+ - - dump/raw/dev_ml/text
89
+ - text
90
+ - text
91
+ allow_variable_data_keys: false
92
+ max_cache_size: 0.0
93
+ max_cache_fd: 32
94
+ valid_max_cache_size: null
95
+ optim: sgd
96
+ optim_conf: {}
97
+ scheduler: null
98
+ scheduler_conf: {}
99
+ token_list:
100
+ - <blank>
101
+ - <unk>
102
+ - ്
103
+ - ാ
104
+ - ി
105
+ - ു
106
+ - ര
107
+ - ▁
108
+ - ം
109
+ - യ
110
+ - ല
111
+ - െ
112
+ - വ
113
+ - ക
114
+ - ത
115
+ - ക്ക
116
+ - ▁അ
117
+ - ന
118
+ - ട
119
+ - മ
120
+ - േ
121
+ - ോ
122
+ - റ
123
+ - ▁പ
124
+ - ർ
125
+ - ണ
126
+ - ▁ക
127
+ - ▁സ
128
+ - ▁മ
129
+ - ത്ത
130
+ - ള
131
+ - ദ
132
+ - ▁വ
133
+ - ും
134
+ - ▁ആ
135
+ - ന്ന
136
+ - സ
137
+ - ത്
138
+ - ീ
139
+ - ▁ത
140
+ - പ
141
+ - ▁ന
142
+ - ന്
143
+ - ൂ
144
+ - ശ
145
+ - ട്ട
146
+ - ിയ
147
+ - ൻ
148
+ - ഗ
149
+ - ‍
150
+ - ▁എന്ന
151
+ - പ്പ
152
+ - തി
153
+ - സ്
154
+ - ്യ
155
+ - ▁ഇ
156
+ - ൽ
157
+ - ങ്ങ
158
+ - റ്റ
159
+ - ുന്ന
160
+ - ഭ
161
+ - ാണ്
162
+ - രി
163
+ - ഹ
164
+ - ണ്ട
165
+ - ത്തി
166
+ - ▁അവ
167
+ - ധ
168
+ - ഷ
169
+ - ▁എ
170
+ - ാന
171
+ - ▁ച
172
+ - ത്ര
173
+ - ▁പ്ര
174
+ - ായി
175
+ - ▁നി
176
+ - മായ
177
+ - ിൽ
178
+ - ▁ഒരു
179
+ - ഥ
180
+ - കള
181
+ - ▁വി
182
+ - ജ
183
+ - ിന്റെ
184
+ - ബ
185
+ - ക്കുന്ന
186
+ - ിച്ച
187
+ - ങ്ങൾ
188
+ - ▁കാ
189
+ - ുണ്ട
190
+ - ുള്ള
191
+ - ായിരുന്നു
192
+ - ച
193
+ - ക്ഷ
194
+ - കൾ
195
+ - ിരുന്ന
196
+ - ല്ല
197
+ - ൾ
198
+ - യും
199
+ - ▁ജ
200
+ - ▁ബ
201
+ - ഡ
202
+ - ച്ച
203
+ - ▁അതിന
204
+ - ുടെ
205
+ - ിച്ചു
206
+ - ൈ
207
+ - ില്ല
208
+ - ▁ശ
209
+ - യിൽ
210
+ - മാണ്
211
+ - യുടെ
212
+ - ത്തിൽ
213
+ - ൃ
214
+ - ഫ
215
+ - ഖ
216
+ - ഠ
217
+ - e
218
+ - ൺ
219
+ - ഘ
220
+ - _
221
+ - '-'
222
+ - ഐ
223
+ - എ
224
+ - n
225
+ - ൌ
226
+ - ഃ
227
+ - അ
228
+ - ഔ
229
+ - ഊ
230
+ - ഛ
231
+ - r
232
+ - l
233
+ - t
234
+ - ഓ
235
+ - ൗ
236
+ - ഏ
237
+ - ഈ
238
+ - ഉ
239
+ - ൊ
240
+ - ഴ
241
+ - ഞ
242
+ - ഒ
243
+ - ഇ
244
+ - ആ
245
+ - ഋ
246
+ - ഝ
247
+ - ങ
248
+ - ഢ
249
+ - <sos/eos>
250
+ init: null
251
+ model_conf:
252
+ ignore_id: 0
253
+ use_preprocessor: true
254
+ token_type: bpe
255
+ bpemodel: data/ml_token_list/bpe_unigram150/bpe.model
256
+ non_linguistic_symbols: null
257
+ cleaner: null
258
+ g2p: null
259
+ lm: seq_rnn
260
+ lm_conf:
261
+ nlayers: 2
262
+ unit: 650
263
+ required:
264
+ - output_dir
265
+ - token_list
266
+ version: 0.10.7a1
267
+ distributed: false
exp/lm_train_lm_ml_bpe150/images/backward_time.png ADDED
exp/lm_train_lm_ml_bpe150/images/forward_time.png ADDED
exp/lm_train_lm_ml_bpe150/images/gpu_max_cached_mem_GB.png ADDED
exp/lm_train_lm_ml_bpe150/images/iter_time.png ADDED
exp/lm_train_lm_ml_bpe150/images/loss.png ADDED
exp/lm_train_lm_ml_bpe150/images/optim0_lr0.png ADDED
exp/lm_train_lm_ml_bpe150/images/optim_step_time.png ADDED
exp/lm_train_lm_ml_bpe150/images/train_time.png ADDED
exp/lm_train_lm_ml_bpe150/valid.loss.ave_1best.pth ADDED
@@ -0,0 +1 @@
 
 
1
+ 30epoch.pth