upload files

data/lang_bpe_500/HLG.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5dbbe8b485c0cb37d11e07e8e734990f1e40a2d00fe9689d8da2e7b6fe72883
+size 845007583

data/lang_bpe_500/L.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b88996f918737fba67fbd29152018b51a537c16ce0718a2b43d5140583224e
+size 19025703

data/lang_bpe_500/LG.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb9f021c7aad79d45dc275ba8154a430c4f660a319dcb872cd52500f25553d6
+size 249852195

data/lang_bpe_500/Linv.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc8b3687a1b8f0811a84106b3b310642566c7b1bc282a929878f9269507a2c6
+size 19025703

data/lang_bpe_500/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c53433de083c4a6ad12d034550ef22de68cec62c4f58932a7b6b8b2f1e743fa5
+size 244865

data/lang_bpe_500/tokens.txt

@@ -0,0 +1,502 @@
+<blk> 0
+<sos/eos> 1
+<unk> 2
+S 3
+▁THE 4
+▁A 5
+T 6
+▁AND 7
+ED 8
+▁OF 9
+▁TO 10
+E 11
+D 12
+N 13
+ING 14
+▁IN 15
+Y 16
+M 17
+C 18
+▁I 19
+A 20
+P 21
+▁HE 22
+R 23
+O 24
+L 25
+RE 26
+I 27
+U 28
+ER 29
+▁IT 30
+LY 31
+▁THAT 32
+▁WAS 33
+▁ 34
+▁S 35
+AR 36
+▁BE 37
+F 38
+▁C 39
+IN 40
+B 41
+▁FOR 42
+OR 43
+LE 44
+' 45
+▁HIS 46
+▁YOU 47
+AL 48
+▁RE 49
+V 50
+▁B 51
+G 52
+RI 53
+▁E 54
+▁WITH 55
+▁T 56
+▁AS 57
+LL 58
+▁P 59
+▁HER 60
+ST 61
+▁HAD 62
+▁SO 63
+▁F 64
+W 65
+CE 66
+▁IS 67
+ND 68
+▁NOT 69
+TH 70
+▁BUT 71
+EN 72
+▁SHE 73
+▁ON 74
+VE 75
+ON 76
+SE 77
+▁DE 78
+UR 79
+▁G 80
+CH 81
+K 82
+TER 83
+▁AT 84
+IT 85
+▁ME 86
+RO 87
+NE 88
+RA 89
+ES 90
+IL 91
+NG 92
+IC 93
+▁NO 94
+▁HIM 95
+ENT 96
+IR 97
+▁WE 98
+H 99
+▁DO 100
+▁ALL 101
+▁HAVE 102
+LO 103
+▁BY 104
+▁MY 105
+▁MO 106
+▁THIS 107
+LA 108
+▁ST 109
+▁WHICH 110
+▁CON 111
+▁THEY 112
+CK 113
+TE 114
+▁SAID 115
+▁FROM 116
+▁GO 117
+▁WHO 118
+▁TH 119
+▁OR 120
+▁D 121
+▁W 122
+VER 123
+LI 124
+▁SE 125
+▁ONE 126
+▁CA 127
+▁AN 128
+▁LA 129
+▁WERE 130
+EL 131
+▁HA 132
+▁MAN 133
+▁FA 134
+▁EX 135
+AD 136
+▁SU 137
+RY 138
+▁MI 139
+AT 140
+▁BO 141
+▁WHEN 142
+AN 143
+THER 144
+PP 145
+ATION 146
+▁FI 147
+▁WOULD 148
+▁PRO 149
+OW 150
+ET 151
+▁O 152
+▁THERE 153
+▁HO 154
+ION 155
+▁WHAT 156
+▁FE 157
+▁PA 158
+US 159
+MENT 160
+▁MA 161
+UT 162
+▁OUT 163
+▁THEIR 164
+▁IF 165
+▁LI 166
+▁K 167
+▁WILL 168
+▁ARE 169
+ID 170
+▁RO 171
+DE 172
+TION 173
+▁WA 174
+PE 175
+▁UP 176
+▁SP 177
+▁PO 178
+IGHT 179
+▁UN 180
+RU 181
+▁LO 182
+AS 183
+OL 184
+▁LE 185
+▁BEEN 186
+▁SH 187
+▁RA 188
+▁SEE 189
+KE 190
+UL 191
+TED 192
+▁SA 193
+UN 194
+UND 195
+ANT 196
+▁NE 197
+IS 198
+▁THEM 199
+CI 200
+GE 201
+▁COULD 202
+▁DIS 203
+OM 204
+ISH 205
+HE 206
+EST 207
+▁SOME 208
+ENCE 209
+ITY 210
+IVE 211
+▁US 212
+▁MORE 213
+▁EN 214
+ARD 215
+ATE 216
+▁YOUR 217
+▁INTO 218
+▁KNOW 219
+▁CO 220
+ANCE 221
+▁TIME 222
+▁WI 223
+▁YE 224
+AGE 225
+▁NOW 226
+TI 227
+FF 228
+ABLE 229
+▁VERY 230
+▁LIKE 231
+AM 232
+HI 233
+Z 234
+▁OTHER 235
+▁THAN 236
+▁LITTLE 237
+▁DID 238
+▁LOOK 239
+TY 240
+ERS 241
+▁CAN 242
+▁CHA 243
+▁AR 244
+X 245
+FUL 246
+UGH 247
+▁BA 248
+▁DAY 249
+▁ABOUT 250
+TEN 251
+IM 252
+▁ANY 253
+▁PRE 254
+▁OVER 255
+IES 256
+NESS 257
+ME 258
+BLE 259
+▁M 260
+ROW 261
+▁HAS 262
+▁GREAT 263
+▁VI 264
+TA 265
+▁AFTER 266
+PER 267
+▁AGAIN 268
+HO 269
+SH 270
+▁UPON 271
+▁DI 272
+▁HAND 273
+▁COM 274
+IST 275
+TURE 276
+▁STA 277
+▁THEN 278
+▁SHOULD 279
+▁GA 280
+OUS 281
+OUR 282
+▁WELL 283
+▁ONLY 284
+MAN 285
+▁GOOD 286
+▁TWO 287
+▁MAR 288
+▁SAY 289
+▁HU 290
+TING 291
+▁OUR 292
+RESS 293
+▁DOWN 294
+IOUS 295
+▁BEFORE 296
+▁DA 297
+▁NA 298
+QUI 299
+▁MADE 300
+▁EVERY 301
+▁OLD 302
+▁EVEN 303
+IG 304
+▁COME 305
+▁GRA 306
+▁RI 307
+▁LONG 308
+OT 309
+SIDE 310
+WARD 311
+▁FO 312
+▁WHERE 313
+MO 314
+LESS 315
+▁SC 316
+▁MUST 317
+▁NEVER 318
+▁HOW 319
+▁CAME 320
+▁SUCH 321
+▁RU 322
+▁TAKE 323
+▁WO 324
+▁CAR 325
+UM 326
+AK 327
+▁THINK 328
+▁MUCH 329
+▁MISTER 330
+▁MAY 331
+▁JO 332
+▁WAY 333
+▁COMP 334
+▁THOUGHT 335
+▁STO 336
+▁MEN 337
+▁BACK 338
+▁DON 339
+J 340
+▁LET 341
+▁TRA 342
+▁FIRST 343
+▁JUST 344
+▁VA 345
+▁OWN 346
+▁PLA 347
+▁MAKE 348
+ATED 349
+▁HIMSELF 350
+▁WENT 351
+▁PI 352
+GG 353
+RING 354
+▁DU 355
+▁MIGHT 356
+▁PART 357
+▁GIVE 358
+▁IMP 359
+▁BU 360
+▁PER 361
+▁PLACE 362
+▁HOUSE 363
+▁THROUGH 364
+IAN 365
+▁SW 366
+▁UNDER 367
+QUE 368
+▁AWAY 369
+▁LOVE 370
+QUA 371
+▁LIFE 372
+▁GET 373
+▁WITHOUT 374
+▁PASS 375
+▁TURN 376
+IGN 377
+▁HEAD 378
+▁MOST 379
+▁THOSE 380
+▁SHALL 381
+▁EYES 382
+▁COL 383
+▁STILL 384
+▁NIGHT 385
+▁NOTHING 386
+ITION 387
+HA 388
+▁TELL 389
+▁WORK 390
+▁LAST 391
+▁NEW 392
+▁FACE 393
+▁HI 394
+▁WORD 395
+▁FOUND 396
+▁COUNT 397
+▁OB 398
+▁WHILE 399
+▁SHA 400
+▁MEAN 401
+▁SAW 402
+▁PEOPLE 403
+▁FRIEND 404
+▁THREE 405
+▁ROOM 406
+▁SAME 407
+▁THOUGH 408
+▁RIGHT 409
+▁CHILD 410
+▁FATHER 411
+▁ANOTHER 412
+▁HEART 413
+▁WANT 414
+▁TOOK 415
+OOK 416
+▁LIGHT 417
+▁MISSUS 418
+▁OPEN 419
+▁JU 420
+▁ASKED 421
+PORT 422
+▁LEFT 423
+▁JA 424
+▁WORLD 425
+▁HOME 426
+▁WHY 427
+▁ALWAYS 428
+▁ANSWER 429
+▁SEEMED 430
+▁SOMETHING 431
+▁GIRL 432
+▁BECAUSE 433
+▁NAME 434
+▁TOLD 435
+▁NI 436
+▁HIGH 437
+IZE 438
+▁WOMAN 439
+▁FOLLOW 440
+▁RETURN 441
+▁KNEW 442
+▁EACH 443
+▁KIND 444
+▁JE 445
+▁ACT 446
+▁LU 447
+▁CERTAIN 448
+▁YEARS 449
+▁QUITE 450
+▁APPEAR 451
+▁BETTER 452
+▁HALF 453
+▁PRESENT 454
+▁PRINCE 455
+SHIP 456
+▁ALSO 457
+▁BEGAN 458
+▁HAVING 459
+▁ENOUGH 460
+▁PERSON 461
+▁LADY 462
+▁WHITE 463
+▁COURSE 464
+▁VOICE 465
+▁SPEAK 466
+▁POWER 467
+▁MORNING 468
+▁BETWEEN 469
+▁AMONG 470
+▁KEEP 471
+▁WALK 472
+▁MATTER 473
+▁TEA 474
+▁BELIEVE 475
+▁SMALL 476
+▁TALK 477
+▁FELT 478
+▁HORSE 479
+▁MYSELF 480
+▁SIX 481
+▁HOWEVER 482
+▁FULL 483
+▁HERSELF 484
+▁POINT 485
+▁STOOD 486
+▁HUNDRED 487
+▁ALMOST 488
+▁SINCE 489
+▁LARGE 490
+▁LEAVE 491
+▁PERHAPS 492
+▁DARK 493
+▁SUDDEN 494
+▁REPLIED 495
+▁ANYTHING 496
+▁WONDER 497
+▁UNTIL 498
+Q 499
+#0 500
+#1 501

data/lm/G_4_gram.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91581bc632f9c72c557ccdf726298255b9627a6ac38270c51891459b82630e9
+size 3700956587

decoding_result/fast_beam_search/log-decode-epoch-30-avg-8-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2023-05-16-15-46-51

@@ -0,0 +1,29 @@
+2023-05-16 15:46:51,536 INFO [decode.py:678] Decoding started
+2023-05-16 15:46:51,536 INFO [decode.py:684] Device: cuda:0
+2023-05-16 15:46:51,540 INFO [decode.py:694] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.24.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'c51a0b9684442a88ee37f3ce0af686a04b66855b', 'k2-git-date': 'Mon May 1 21:38:03 2023', 'lhotse-version': '1.12.0.dev+git.891bad1.clean', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'zipformer2_from_dan', 'icefall-git-sha1': '85d51991-dirty', 'icefall-git-date': 'Tue May 16 14:39:13 2023', 'icefall-path': '/ceph-zw/workspace/zipformer/icefall_zipformer', 'k2-path': '/ceph-zw/workspace/k2/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-zw/workspace/share/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mlpzc', 'IP address': '10.177.22.19'}, 'epoch': 30, 'iter': 0, 'avg': 8, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-small'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'fast_beam_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,2,2,2,2,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,768,768,768,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,256,256,256,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,192,192,192,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'drop_last': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'input_strategy': 'PrecomputedFeatures', 'res_dir': PosixPath('zipformer/exp-small/fast_beam_search'), 'suffix': 'epoch-30-avg-8-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-05-16 15:46:51,540 INFO [decode.py:696] About to create model
+2023-05-16 15:46:51,945 INFO [decode.py:763] Calculating the averaged model over epoch range from 22 (excluded) to 30
+2023-05-16 15:46:57,444 INFO [decode.py:799] Number of model parameters: 23285615
+2023-05-16 15:46:57,444 INFO [asr_datamodule.py:465] About to get test-clean cuts
+2023-05-16 15:46:57,446 INFO [asr_datamodule.py:472] About to get test-other cuts
+2023-05-16 15:46:59,684 INFO [decode.py:570] batch 0/?, cuts processed until now is 43
+2023-05-16 15:47:26,676 INFO [decode.py:570] batch 20/?, cuts processed until now is 1430
+2023-05-16 15:47:54,496 INFO [decode.py:570] batch 40/?, cuts processed until now is 2574
+2023-05-16 15:47:55,460 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-30-avg-8-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-05-16 15:47:55,530 INFO [utils.py:558] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 2.62% [1375 / 52576, 155 ins, 114 del, 1106 sub ]
+2023-05-16 15:47:55,711 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-30-avg-8-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-05-16 15:47:55,712 INFO [decode.py:618] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	2.62	best for test-clean
+
+2023-05-16 15:47:57,440 INFO [decode.py:570] batch 0/?, cuts processed until now is 52
+2023-05-16 15:48:22,085 INFO [decode.py:570] batch 20/?, cuts processed until now is 1646
+2023-05-16 15:48:48,482 INFO [decode.py:570] batch 40/?, cuts processed until now is 2870
+2023-05-16 15:48:49,306 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-30-avg-8-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-05-16 15:48:49,378 INFO [utils.py:558] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 6.06% [3171 / 52343, 341 ins, 271 del, 2559 sub ]
+2023-05-16 15:48:49,554 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-30-avg-8-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-05-16 15:48:49,555 INFO [decode.py:618] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	6.06	best for test-other
+
+2023-05-16 15:48:49,555 INFO [decode.py:830] Done!

decoding_result/fast_beam_search/log-decode-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2023-05-12-19-54-08

@@ -0,0 +1,31 @@
+2023-05-12 19:54:08,395 INFO [decode.py:678] Decoding started
+2023-05-12 19:54:08,396 INFO [decode.py:684] Device: cuda:0
+2023-05-12 19:54:08,399 INFO [decode.py:694] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.23.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '7efe024b23078ffa0bcb5598afff14f356edae7c', 'k2-git-date': 'Mon Jan 30 20:22:57 2023', 'lhotse-version': '1.12.0.dev+git.891bad1.clean', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'zipformer2_from_dan', 'icefall-git-sha1': 'ec211286-clean', 'icefall-git-date': 'Fri May 12 18:45:00 2023', 'icefall-path': '/ceph-zw/workspace/zipformer/icefall_zipformer', 'k2-path': '/ceph-zw/workspace/k2/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-zw/workspace/share/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mlpzc', 'IP address': '10.177.22.19'}, 'epoch': 40, 'iter': 0, 'avg': 13, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-small'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'fast_beam_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,2,2,2,2,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,768,768,768,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,256,256,256,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,192,192,192,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'drop_last': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'input_strategy': 'PrecomputedFeatures', 'res_dir': PosixPath('zipformer/exp-small/fast_beam_search'), 'suffix': 'epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-05-12 19:54:08,399 INFO [decode.py:696] About to create model
+2023-05-12 19:54:08,717 INFO [decode.py:763] Calculating the averaged model over epoch range from 27 (excluded) to 40
+2023-05-12 19:54:17,225 INFO [decode.py:799] Number of model parameters: 23285615
+2023-05-12 19:54:17,225 INFO [asr_datamodule.py:465] About to get test-clean cuts
+2023-05-12 19:54:17,227 INFO [asr_datamodule.py:472] About to get test-other cuts
+2023-05-12 19:54:19,489 INFO [decode.py:570] batch 0/?, cuts processed until now is 43
+2023-05-12 19:54:50,250 INFO [decode.py:570] batch 20/?, cuts processed until now is 1430
+2023-05-12 19:55:26,411 INFO [decode.py:570] batch 40/?, cuts processed until now is 2574
+2023-05-12 19:55:27,646 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-05-12 19:55:27,719 INFO [utils.py:558] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 2.46% [1293 / 52576, 140 ins, 99 del, 1054 sub ]
+2023-05-12 19:55:27,901 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-05-12 19:55:27,902 INFO [decode.py:618] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	2.46	best for test-clean
+
+2023-05-12 19:55:30,060 INFO [decode.py:570] batch 0/?, cuts processed until now is 52
+2023-05-12 19:55:31,589 INFO [zipformer.py:1655] name=None, attn_weights_entropy = tensor([1.7907, 2.3585, 2.2052, 2.4565, 1.4741, 2.4270, 2.5435, 2.4639],
+       device='cuda:0')
+2023-05-12 19:55:56,008 INFO [decode.py:570] batch 20/?, cuts processed until now is 1646
+2023-05-12 19:56:24,127 INFO [decode.py:570] batch 40/?, cuts processed until now is 2870
+2023-05-12 19:56:25,044 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-05-12 19:56:25,118 INFO [utils.py:558] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 5.87% [3073 / 52343, 320 ins, 252 del, 2501 sub ]
+2023-05-12 19:56:25,296 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-05-12 19:56:25,297 INFO [decode.py:618] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	5.87	best for test-other
+
+2023-05-12 19:56:25,297 INFO [decode.py:830] Done!

decoding_result/fast_beam_search/wer-summary-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-30-avg-8-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_20.0_max_contexts_8_max_states_64	2.62

decoding_result/fast_beam_search/wer-summary-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_20.0_max_contexts_8_max_states_64	2.46

decoding_result/fast_beam_search/wer-summary-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-30-avg-8-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_20.0_max_contexts_8_max_states_64	6.06

decoding_result/fast_beam_search/wer-summary-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_20.0_max_contexts_8_max_states_64	5.87

decoding_result/greedy_search/log-decode-epoch-30-avg-8-context-2-max-sym-per-frame-1-use-averaged-model-2023-05-16-15-39-34

@@ -0,0 +1,26 @@
+2023-05-16 15:39:34,223 INFO [decode.py:678] Decoding started
+2023-05-16 15:39:34,223 INFO [decode.py:684] Device: cuda:0
+2023-05-16 15:39:34,226 INFO [decode.py:694] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.24.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'c51a0b9684442a88ee37f3ce0af686a04b66855b', 'k2-git-date': 'Mon May 1 21:38:03 2023', 'lhotse-version': '1.12.0.dev+git.891bad1.clean', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'zipformer2_from_dan', 'icefall-git-sha1': '85d51991-dirty', 'icefall-git-date': 'Tue May 16 14:39:13 2023', 'icefall-path': '/ceph-zw/workspace/zipformer/icefall_zipformer', 'k2-path': '/ceph-zw/workspace/k2/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-zw/workspace/share/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mlpzc', 'IP address': '10.177.22.19'}, 'epoch': 30, 'iter': 0, 'avg': 8, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-small'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'greedy_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,2,2,2,2,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,768,768,768,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,256,256,256,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,192,192,192,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'drop_last': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'input_strategy': 'PrecomputedFeatures', 'res_dir': PosixPath('zipformer/exp-small/greedy_search'), 'suffix': 'epoch-30-avg-8-context-2-max-sym-per-frame-1-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-05-16 15:39:34,227 INFO [decode.py:696] About to create model
+2023-05-16 15:39:34,605 INFO [decode.py:763] Calculating the averaged model over epoch range from 22 (excluded) to 30
+2023-05-16 15:39:41,912 INFO [decode.py:799] Number of model parameters: 23285615
+2023-05-16 15:39:41,913 INFO [asr_datamodule.py:465] About to get test-clean cuts
+2023-05-16 15:39:41,915 INFO [asr_datamodule.py:472] About to get test-other cuts
+2023-05-16 15:39:43,358 INFO [decode.py:570] batch 0/?, cuts processed until now is 43
+2023-05-16 15:39:57,081 INFO [zipformer.py:1711] name=None, attn_weights_entropy = tensor([5.5713, 4.8848, 4.9966, 5.1667], device='cuda:0')
+2023-05-16 15:40:08,886 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/greedy_search/recogs-test-clean-greedy_search-epoch-30-avg-8-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-05-16 15:40:08,959 INFO [utils.py:558] [test-clean-greedy_search] %WER 2.64% [1389 / 52576, 149 ins, 123 del, 1117 sub ]
+2023-05-16 15:40:09,134 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/greedy_search/errs-test-clean-greedy_search-epoch-30-avg-8-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-05-16 15:40:09,134 INFO [decode.py:618] 
+For test-clean, WER of different settings are:
+greedy_search	2.64	best for test-clean
+
+2023-05-16 15:40:10,257 INFO [decode.py:570] batch 0/?, cuts processed until now is 52
+2023-05-16 15:40:34,246 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/greedy_search/recogs-test-other-greedy_search-epoch-30-avg-8-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-05-16 15:40:34,325 INFO [utils.py:558] [test-other-greedy_search] %WER 6.14% [3216 / 52343, 316 ins, 284 del, 2616 sub ]
+2023-05-16 15:40:34,507 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/greedy_search/errs-test-other-greedy_search-epoch-30-avg-8-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-05-16 15:40:34,507 INFO [decode.py:618] 
+For test-other, WER of different settings are:
+greedy_search	6.14	best for test-other
+
+2023-05-16 15:40:34,507 INFO [decode.py:830] Done!

decoding_result/greedy_search/log-decode-epoch-40-avg-13-context-2-max-sym-per-frame-1-use-averaged-model-2023-05-16-15-33-32

@@ -0,0 +1,25 @@
+2023-05-16 15:33:32,428 INFO [decode.py:678] Decoding started
+2023-05-16 15:33:32,428 INFO [decode.py:684] Device: cuda:0
+2023-05-16 15:33:32,431 INFO [decode.py:694] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.24.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'c51a0b9684442a88ee37f3ce0af686a04b66855b', 'k2-git-date': 'Mon May 1 21:38:03 2023', 'lhotse-version': '1.12.0.dev+git.891bad1.clean', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'zipformer2_from_dan', 'icefall-git-sha1': '85d51991-dirty', 'icefall-git-date': 'Tue May 16 14:39:13 2023', 'icefall-path': '/ceph-zw/workspace/zipformer/icefall_zipformer', 'k2-path': '/ceph-zw/workspace/k2/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-zw/workspace/share/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mlpzc', 'IP address': '10.177.22.19'}, 'epoch': 40, 'iter': 0, 'avg': 13, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-small'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'greedy_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,2,2,2,2,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,768,768,768,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,256,256,256,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,192,192,192,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'drop_last': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'input_strategy': 'PrecomputedFeatures', 'res_dir': PosixPath('zipformer/exp-small/greedy_search'), 'suffix': 'epoch-40-avg-13-context-2-max-sym-per-frame-1-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-05-16 15:33:32,431 INFO [decode.py:696] About to create model
+2023-05-16 15:33:32,825 INFO [decode.py:763] Calculating the averaged model over epoch range from 27 (excluded) to 40
+2023-05-16 15:33:41,301 INFO [decode.py:799] Number of model parameters: 23285615
+2023-05-16 15:33:41,302 INFO [asr_datamodule.py:465] About to get test-clean cuts
+2023-05-16 15:33:41,304 INFO [asr_datamodule.py:472] About to get test-other cuts
+2023-05-16 15:33:42,779 INFO [decode.py:570] batch 0/?, cuts processed until now is 43
+2023-05-16 15:34:08,648 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/greedy_search/recogs-test-clean-greedy_search-epoch-40-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-05-16 15:34:08,722 INFO [utils.py:558] [test-clean-greedy_search] %WER 2.49% [1310 / 52576, 137 ins, 110 del, 1063 sub ]
+2023-05-16 15:34:08,896 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/greedy_search/errs-test-clean-greedy_search-epoch-40-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-05-16 15:34:08,896 INFO [decode.py:618] 
+For test-clean, WER of different settings are:
+greedy_search	2.49	best for test-clean
+
+2023-05-16 15:34:09,999 INFO [decode.py:570] batch 0/?, cuts processed until now is 52
+2023-05-16 15:34:33,663 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/greedy_search/recogs-test-other-greedy_search-epoch-40-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-05-16 15:34:33,745 INFO [utils.py:558] [test-other-greedy_search] %WER 5.91% [3094 / 52343, 305 ins, 266 del, 2523 sub ]
+2023-05-16 15:34:33,925 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/greedy_search/errs-test-other-greedy_search-epoch-40-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-05-16 15:34:33,926 INFO [decode.py:618] 
+For test-other, WER of different settings are:
+greedy_search	5.91	best for test-other
+
+2023-05-16 15:34:33,926 INFO [decode.py:830] Done!

decoding_result/greedy_search/wer-summary-test-clean-greedy_search-epoch-30-avg-8-context-2-max-sym-per-frame-1-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search	2.64

decoding_result/greedy_search/wer-summary-test-clean-greedy_search-epoch-40-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search	2.49

decoding_result/greedy_search/wer-summary-test-other-greedy_search-epoch-30-avg-8-context-2-max-sym-per-frame-1-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search	6.14

decoding_result/greedy_search/wer-summary-test-other-greedy_search-epoch-40-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search	5.91

decoding_result/modified_beam_search/log-decode-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model-2023-05-16-15-41-47

@@ -0,0 +1,31 @@
+2023-05-16 15:41:47,629 INFO [decode.py:678] Decoding started
+2023-05-16 15:41:47,629 INFO [decode.py:684] Device: cuda:0
+2023-05-16 15:41:47,632 INFO [decode.py:694] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.24.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'c51a0b9684442a88ee37f3ce0af686a04b66855b', 'k2-git-date': 'Mon May 1 21:38:03 2023', 'lhotse-version': '1.12.0.dev+git.891bad1.clean', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'zipformer2_from_dan', 'icefall-git-sha1': '85d51991-dirty', 'icefall-git-date': 'Tue May 16 14:39:13 2023', 'icefall-path': '/ceph-zw/workspace/zipformer/icefall_zipformer', 'k2-path': '/ceph-zw/workspace/k2/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-zw/workspace/share/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mlpzc', 'IP address': '10.177.22.19'}, 'epoch': 30, 'iter': 0, 'avg': 8, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-small'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'modified_beam_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,2,2,2,2,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,768,768,768,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,256,256,256,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,192,192,192,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'drop_last': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'input_strategy': 'PrecomputedFeatures', 'res_dir': PosixPath('zipformer/exp-small/modified_beam_search'), 'suffix': 'epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-05-16 15:41:47,632 INFO [decode.py:696] About to create model
+2023-05-16 15:41:48,028 INFO [decode.py:763] Calculating the averaged model over epoch range from 22 (excluded) to 30
+2023-05-16 15:41:53,415 INFO [decode.py:799] Number of model parameters: 23285615
+2023-05-16 15:41:53,415 INFO [asr_datamodule.py:465] About to get test-clean cuts
+2023-05-16 15:41:53,417 INFO [asr_datamodule.py:472] About to get test-other cuts
+2023-05-16 15:41:57,779 INFO [decode.py:570] batch 0/?, cuts processed until now is 43
+2023-05-16 15:42:59,578 INFO [zipformer.py:1711] name=None, attn_weights_entropy = tensor([2.7639, 3.0905, 3.5930, 3.2426], device='cuda:0')
+2023-05-16 15:43:05,973 INFO [decode.py:570] batch 20/?, cuts processed until now is 1430
+2023-05-16 15:44:01,839 INFO [decode.py:570] batch 40/?, cuts processed until now is 2574
+2023-05-16 15:44:04,161 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/modified_beam_search/recogs-test-clean-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-05-16 15:44:04,241 INFO [utils.py:558] [test-clean-beam_size_4] %WER 2.60% [1366 / 52576, 152 ins, 106 del, 1108 sub ]
+2023-05-16 15:44:04,415 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/modified_beam_search/errs-test-clean-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-05-16 15:44:04,416 INFO [decode.py:618] 
+For test-clean, WER of different settings are:
+beam_size_4	2.6	best for test-clean
+
+2023-05-16 15:44:08,409 INFO [decode.py:570] batch 0/?, cuts processed until now is 52
+2023-05-16 15:44:49,023 INFO [zipformer.py:1711] name=None, attn_weights_entropy = tensor([4.9292, 4.6428, 4.1287, 4.5603], device='cuda:0')
+2023-05-16 15:45:14,322 INFO [decode.py:570] batch 20/?, cuts processed until now is 1646
+2023-05-16 15:46:08,534 INFO [decode.py:570] batch 40/?, cuts processed until now is 2870
+2023-05-16 15:46:10,635 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/modified_beam_search/recogs-test-other-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-05-16 15:46:10,800 INFO [utils.py:558] [test-other-beam_size_4] %WER 6.01% [3146 / 52343, 336 ins, 259 del, 2551 sub ]
+2023-05-16 15:46:10,980 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/modified_beam_search/errs-test-other-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-05-16 15:46:10,981 INFO [decode.py:618] 
+For test-other, WER of different settings are:
+beam_size_4	6.01	best for test-other
+
+2023-05-16 15:46:10,981 INFO [decode.py:830] Done!

decoding_result/modified_beam_search/log-decode-epoch-40-avg-13-modified_beam_search-beam-size-4-use-averaged-model-2023-05-12-19-56-52

@@ -0,0 +1,31 @@
+2023-05-12 19:56:52,790 INFO [decode.py:678] Decoding started
+2023-05-12 19:56:52,790 INFO [decode.py:684] Device: cuda:0
+2023-05-12 19:56:52,793 INFO [decode.py:694] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.23.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '7efe024b23078ffa0bcb5598afff14f356edae7c', 'k2-git-date': 'Mon Jan 30 20:22:57 2023', 'lhotse-version': '1.12.0.dev+git.891bad1.clean', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'zipformer2_from_dan', 'icefall-git-sha1': 'ec211286-clean', 'icefall-git-date': 'Fri May 12 18:45:00 2023', 'icefall-path': '/ceph-zw/workspace/zipformer/icefall_zipformer', 'k2-path': '/ceph-zw/workspace/k2/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-zw/workspace/share/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mlpzc', 'IP address': '10.177.22.19'}, 'epoch': 40, 'iter': 0, 'avg': 13, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-small'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'modified_beam_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,2,2,2,2,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,768,768,768,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,256,256,256,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,192,192,192,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'drop_last': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'input_strategy': 'PrecomputedFeatures', 'res_dir': PosixPath('zipformer/exp-small/modified_beam_search'), 'suffix': 'epoch-40-avg-13-modified_beam_search-beam-size-4-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-05-12 19:56:52,793 INFO [decode.py:696] About to create model
+2023-05-12 19:56:53,115 INFO [decode.py:763] Calculating the averaged model over epoch range from 27 (excluded) to 40
+2023-05-12 19:56:58,901 INFO [decode.py:799] Number of model parameters: 23285615
+2023-05-12 19:56:58,901 INFO [asr_datamodule.py:465] About to get test-clean cuts
+2023-05-12 19:56:58,903 INFO [asr_datamodule.py:472] About to get test-other cuts
+2023-05-12 19:57:03,238 INFO [decode.py:570] batch 0/?, cuts processed until now is 43
+2023-05-12 19:58:13,188 INFO [decode.py:570] batch 20/?, cuts processed until now is 1430
+2023-05-12 19:58:20,620 INFO [zipformer.py:1655] name=None, attn_weights_entropy = tensor([3.7557, 3.9278, 3.8564, 4.6704, 3.6542, 4.2698, 4.6970, 4.2007],
+       device='cuda:0')
+2023-05-12 19:59:24,812 INFO [decode.py:570] batch 40/?, cuts processed until now is 2574
+2023-05-12 19:59:27,560 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/modified_beam_search/recogs-test-clean-beam_size_4-epoch-40-avg-13-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-05-12 19:59:27,643 INFO [utils.py:558] [test-clean-beam_size_4] %WER 2.46% [1293 / 52576, 143 ins, 103 del, 1047 sub ]
+2023-05-12 19:59:27,825 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/modified_beam_search/errs-test-clean-beam_size_4-epoch-40-avg-13-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-05-12 19:59:27,825 INFO [decode.py:618] 
+For test-clean, WER of different settings are:
+beam_size_4	2.46	best for test-clean
+
+2023-05-12 19:59:32,962 INFO [decode.py:570] batch 0/?, cuts processed until now is 52
+2023-05-12 20:00:47,927 INFO [decode.py:570] batch 20/?, cuts processed until now is 1646
+2023-05-12 20:01:43,007 INFO [decode.py:570] batch 40/?, cuts processed until now is 2870
+2023-05-12 20:01:45,297 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/modified_beam_search/recogs-test-other-beam_size_4-epoch-40-avg-13-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-05-12 20:01:45,382 INFO [utils.py:558] [test-other-beam_size_4] %WER 5.83% [3049 / 52343, 318 ins, 242 del, 2489 sub ]
+2023-05-12 20:01:45,564 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/modified_beam_search/errs-test-other-beam_size_4-epoch-40-avg-13-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-05-12 20:01:45,565 INFO [decode.py:618] 
+For test-other, WER of different settings are:
+beam_size_4	5.83	best for test-other
+
+2023-05-12 20:01:45,565 INFO [decode.py:830] Done!

decoding_result/modified_beam_search/wer-summary-test-clean-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_size_4	2.6

decoding_result/modified_beam_search/wer-summary-test-clean-beam_size_4-epoch-40-avg-13-modified_beam_search-beam-size-4-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_size_4	2.46

decoding_result/modified_beam_search/wer-summary-test-other-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_size_4	6.01

decoding_result/modified_beam_search/wer-summary-test-other-beam_size_4-epoch-40-avg-13-modified_beam_search-beam-size-4-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_size_4	5.83