upload files

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_results/1best/log-decode-epoch-25-avg-7-use-averaged-model-2022-11-27-20-52-40

@@ -0,0 +1,9 @@
+2022-11-27 20:52:40,519 INFO [decode.py:786] Decoding started
+2022-11-27 20:52:40,519 INFO [decode.py:792] Device: cuda:0
+2022-11-27 20:52:40,519 INFO [decode.py:793] {'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, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'beam_size': 10, 'reduction': 'sum', 'use_double_scores': True, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.21', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '409a24f9035df693583f9b3fea17a5934bdb3bbf', 'k2-git-date': 'Wed Nov 2 18:17:39 2022', 'lhotse-version': '1.4.0.dev+git.21b5b3f.dirty', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'latency_k2_ctc', 'icefall-git-sha1': '7817199-dirty', 'icefall-git-date': 'Tue Nov 22 20:35:37 2022', 'icefall-path': '/ceph-zw/workspace/latency/icefall_k2_ctc', 'k2-path': '/ceph-zw/workspace/latency/k2_ctc_latency/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-jb/yaozengwei/workspace/rnnt/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-2-0602201035-5fb6d86964-mclm7', 'IP address': '10.177.74.202'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'epoch': 25, 'iter': 0, 'avg': 7, 'use_averaged_model': True, 'exp_dir': PosixPath('conformer_ctc3/exp-full'), 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': '1best', 'num_paths': 100, 'nbest_scale': 0.5, 'lm_dir': PosixPath('data/my_lm'), 'simulate_streaming': False, 'decode_chunk_size': 32, 'left_context': 128, 'dynamic_chunk_training': False, 'causal_convolution': False, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank_ali'), 'max_duration': 300, '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('conformer_ctc3/exp-full/1best'), 'suffix': 'epoch-25-avg-7-use-averaged-model'}
+2022-11-27 20:52:40,813 INFO [lexicon.py:176] Loading pre-compiled data/lang_bpe_500/Linv.pt
+2022-11-27 20:52:50,123 INFO [decode.py:879] About to create model
+2022-11-27 20:52:50,523 INFO [decode.py:946] Calculating the averaged model over epoch range from 18 (excluded) to 25
+2022-11-27 20:52:52,472 INFO [decode.py:963] Number of model parameters: 77352694
+2022-11-27 20:52:52,472 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-11-27 20:52:52,475 INFO [asr_datamodule.py:451] About to get test-other cuts

decoding_results/1best/log-decode-epoch-25-avg-7-use-averaged-model-2022-11-27-21-02-34

@@ -0,0 +1,84 @@
+2022-11-27 21:02:34,010 INFO [decode.py:795] Decoding started
+2022-11-27 21:02:34,010 INFO [decode.py:801] Device: cuda:0
+2022-11-27 21:02:34,010 INFO [decode.py:802] {'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, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'beam_size': 10, 'reduction': 'sum', 'use_double_scores': True, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.21', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '409a24f9035df693583f9b3fea17a5934bdb3bbf', 'k2-git-date': 'Wed Nov 2 18:17:39 2022', 'lhotse-version': '1.4.0.dev+git.21b5b3f.dirty', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'latency_k2_ctc', 'icefall-git-sha1': '7817199-dirty', 'icefall-git-date': 'Tue Nov 22 20:35:37 2022', 'icefall-path': '/ceph-zw/workspace/latency/icefall_k2_ctc', 'k2-path': '/ceph-zw/workspace/latency/k2_ctc_latency/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-jb/yaozengwei/workspace/rnnt/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-2-0602201035-5fb6d86964-mclm7', 'IP address': '10.177.74.202'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'epoch': 25, 'iter': 0, 'avg': 7, 'use_averaged_model': True, 'exp_dir': PosixPath('conformer_ctc3/exp-full'), 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': '1best', 'num_paths': 100, 'nbest_scale': 0.5, 'lm_dir': PosixPath('data/my_lm'), 'simulate_streaming': False, 'decode_chunk_size': 32, 'left_context': 128, 'dynamic_chunk_training': False, 'causal_convolution': False, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank_ali'), 'max_duration': 300, '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('conformer_ctc3/exp-full/1best'), 'suffix': 'epoch-25-avg-7-use-averaged-model'}
+2022-11-27 21:02:34,286 INFO [lexicon.py:176] Loading pre-compiled data/lang_bpe_500/Linv.pt
+2022-11-27 21:02:39,559 INFO [decode.py:888] About to create model
+2022-11-27 21:02:39,914 INFO [decode.py:955] Calculating the averaged model over epoch range from 18 (excluded) to 25
+2022-11-27 21:02:42,070 INFO [decode.py:972] Number of model parameters: 77352694
+2022-11-27 21:02:42,070 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-11-27 21:02:42,072 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-11-27 21:02:44,657 INFO [decode.py:674] batch 0/?, cuts processed until now is 23
+2022-11-27 21:04:12,591 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-clean-no-rescore-HLG-scale-0.2-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:12,708 INFO [utils.py:731] [test-clean-no-rescore-HLG-scale-0.2] %WER 2.95% [1551 / 52576, 265 ins, 89 del, 1197 sub ]
+2022-11-27 21:04:12,709 INFO [utils.py:736] [test-clean-no-rescore-HLG-scale-0.2] %symbol-delay mean: 0.115s, variance: 0.023 computed on 51290 correct words
+2022-11-27 21:04:12,922 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-clean-no-rescore-HLG-scale-0.2-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:13,004 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-clean-no-rescore-HLG-scale-0.4-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:13,111 INFO [utils.py:731] [test-clean-no-rescore-HLG-scale-0.4] %WER 2.89% [1521 / 52576, 242 ins, 102 del, 1177 sub ]
+2022-11-27 21:04:13,111 INFO [utils.py:736] [test-clean-no-rescore-HLG-scale-0.4] %symbol-delay mean: 0.115s, variance: 0.023 computed on 51297 correct words
+2022-11-27 21:04:13,297 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-clean-no-rescore-HLG-scale-0.4-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:13,369 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-clean-no-rescore-HLG-scale-0.6-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:13,472 INFO [utils.py:731] [test-clean-no-rescore-HLG-scale-0.6] %WER 2.87% [1510 / 52576, 219 ins, 120 del, 1171 sub ]
+2022-11-27 21:04:13,472 INFO [utils.py:736] [test-clean-no-rescore-HLG-scale-0.6] %symbol-delay mean: 0.115s, variance: 0.023 computed on 51285 correct words
+2022-11-27 21:04:13,657 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-clean-no-rescore-HLG-scale-0.6-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:13,731 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-clean-no-rescore-HLG-scale-0.8-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:13,836 INFO [utils.py:731] [test-clean-no-rescore-HLG-scale-0.8] %WER 2.94% [1546 / 52576, 206 ins, 151 del, 1189 sub ]
+2022-11-27 21:04:13,836 INFO [utils.py:736] [test-clean-no-rescore-HLG-scale-0.8] %symbol-delay mean: 0.115s, variance: 0.023 computed on 51236 correct words
+2022-11-27 21:04:14,019 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-clean-no-rescore-HLG-scale-0.8-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:14,090 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-clean-no-rescore-HLG-scale-1.0-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:14,190 INFO [utils.py:731] [test-clean-no-rescore-HLG-scale-1.0] %WER 3.07% [1613 / 52576, 180 ins, 203 del, 1230 sub ]
+2022-11-27 21:04:14,190 INFO [utils.py:736] [test-clean-no-rescore-HLG-scale-1.0] %symbol-delay mean: 0.115s, variance: 0.023 computed on 51143 correct words
+2022-11-27 21:04:14,465 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-clean-no-rescore-HLG-scale-1.0-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:04:14,466 INFO [decode.py:740] 
+For test-clean, WER of different settings are:
+no-rescore-HLG-scale-0.6	2.87	best for test-clean
+no-rescore-HLG-scale-0.4	2.89
+no-rescore-HLG-scale-0.8	2.94
+no-rescore-HLG-scale-0.2	2.95
+no-rescore-HLG-scale-1.0	3.07
+
+2022-11-27 21:04:14,466 INFO [decode.py:749] 
+For test-clean, symbol-delay of different settings are:
+no-rescore-HLG-scale-0.2	mean: 0.115s, variance: 0.023	best for test-clean
+no-rescore-HLG-scale-0.4	mean: 0.115s, variance: 0.023
+no-rescore-HLG-scale-0.6	mean: 0.115s, variance: 0.023
+no-rescore-HLG-scale-0.8	mean: 0.115s, variance: 0.023
+no-rescore-HLG-scale-1.0	mean: 0.115s, variance: 0.023
+
+2022-11-27 21:04:16,609 INFO [decode.py:674] batch 0/?, cuts processed until now is 29
+2022-11-27 21:05:50,376 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-other-no-rescore-HLG-scale-0.2-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:50,605 INFO [utils.py:731] [test-other-no-rescore-HLG-scale-0.2] %WER 6.68% [3499 / 52343, 447 ins, 266 del, 2786 sub ]
+2022-11-27 21:05:50,605 INFO [utils.py:736] [test-other-no-rescore-HLG-scale-0.2] %symbol-delay mean: 0.098s, variance: 0.019 computed on 49273 correct words
+2022-11-27 21:05:50,830 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-other-no-rescore-HLG-scale-0.2-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:50,926 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-other-no-rescore-HLG-scale-0.4-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:51,044 INFO [utils.py:731] [test-other-no-rescore-HLG-scale-0.4] %WER 6.47% [3385 / 52343, 380 ins, 321 del, 2684 sub ]
+2022-11-27 21:05:51,044 INFO [utils.py:736] [test-other-no-rescore-HLG-scale-0.4] %symbol-delay mean: 0.098s, variance: 0.019 computed on 49320 correct words
+2022-11-27 21:05:51,269 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-other-no-rescore-HLG-scale-0.4-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:51,343 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-other-no-rescore-HLG-scale-0.6-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:51,446 INFO [utils.py:731] [test-other-no-rescore-HLG-scale-0.6] %WER 6.44% [3373 / 52343, 330 ins, 389 del, 2654 sub ]
+2022-11-27 21:05:51,446 INFO [utils.py:736] [test-other-no-rescore-HLG-scale-0.6] %symbol-delay mean: 0.098s, variance: 0.019 computed on 49282 correct words
+2022-11-27 21:05:51,668 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-other-no-rescore-HLG-scale-0.6-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:51,741 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-other-no-rescore-HLG-scale-0.8-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:51,860 INFO [utils.py:731] [test-other-no-rescore-HLG-scale-0.8] %WER 6.54% [3423 / 52343, 294 ins, 475 del, 2654 sub ]
+2022-11-27 21:05:51,860 INFO [utils.py:736] [test-other-no-rescore-HLG-scale-0.8] %symbol-delay mean: 0.098s, variance: 0.019 computed on 49196 correct words
+2022-11-27 21:05:52,090 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-other-no-rescore-HLG-scale-0.8-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:52,163 INFO [decode.py:696] The transcripts are stored in conformer_ctc3/exp-full/1best/recogs-test-other-no-rescore-HLG-scale-1.0-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:52,294 INFO [utils.py:731] [test-other-no-rescore-HLG-scale-1.0] %WER 6.86% [3593 / 52343, 283 ins, 617 del, 2693 sub ]
+2022-11-27 21:05:52,294 INFO [utils.py:736] [test-other-no-rescore-HLG-scale-1.0] %symbol-delay mean: 0.098s, variance: 0.019 computed on 49015 correct words
+2022-11-27 21:05:52,489 INFO [decode.py:710] Wrote detailed error stats to conformer_ctc3/exp-full/1best/errs-test-other-no-rescore-HLG-scale-1.0-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 21:05:52,490 INFO [decode.py:740] 
+For test-other, WER of different settings are:
+no-rescore-HLG-scale-0.6	6.44	best for test-other
+no-rescore-HLG-scale-0.4	6.47
+no-rescore-HLG-scale-0.8	6.54
+no-rescore-HLG-scale-0.2	6.68
+no-rescore-HLG-scale-1.0	6.86
+
+2022-11-27 21:05:52,490 INFO [decode.py:749] 
+For test-other, symbol-delay of different settings are:
+no-rescore-HLG-scale-0.2	mean: 0.098s, variance: 0.019	best for test-other
+no-rescore-HLG-scale-0.4	mean: 0.098s, variance: 0.019
+no-rescore-HLG-scale-0.6	mean: 0.098s, variance: 0.019
+no-rescore-HLG-scale-0.8	mean: 0.098s, variance: 0.019
+no-rescore-HLG-scale-1.0	mean: 0.098s, variance: 0.019
+
+2022-11-27 21:05:52,490 INFO [decode.py:1007] Done!

decoding_results/1best/symbol-delay-summary-test-clean-no-rescore-HLG-scale-1.0-epoch-25-avg-7-use-averaged-model.txt

@@ -0,0 +1,6 @@
+settings	symbol-delay
+no-rescore-HLG-scale-0.2	mean: 0.115s, variance: 0.023
+no-rescore-HLG-scale-0.4	mean: 0.115s, variance: 0.023
+no-rescore-HLG-scale-0.6	mean: 0.115s, variance: 0.023
+no-rescore-HLG-scale-0.8	mean: 0.115s, variance: 0.023
+no-rescore-HLG-scale-1.0	mean: 0.115s, variance: 0.023

decoding_results/1best/symbol-delay-summary-test-other-no-rescore-HLG-scale-1.0-epoch-25-avg-7-use-averaged-model.txt

@@ -0,0 +1,6 @@
+settings	symbol-delay
+no-rescore-HLG-scale-0.2	mean: 0.098s, variance: 0.019
+no-rescore-HLG-scale-0.4	mean: 0.098s, variance: 0.019
+no-rescore-HLG-scale-0.6	mean: 0.098s, variance: 0.019
+no-rescore-HLG-scale-0.8	mean: 0.098s, variance: 0.019
+no-rescore-HLG-scale-1.0	mean: 0.098s, variance: 0.019

decoding_results/1best/wer-summary-test-clean-no-rescore-HLG-scale-1.0-epoch-25-avg-7-use-averaged-model.txt

@@ -0,0 +1,6 @@
+settings	WER
+no-rescore-HLG-scale-0.6	2.87
+no-rescore-HLG-scale-0.4	2.89
+no-rescore-HLG-scale-0.8	2.94
+no-rescore-HLG-scale-0.2	2.95
+no-rescore-HLG-scale-1.0	3.07

decoding_results/1best/wer-summary-test-other-no-rescore-HLG-scale-1.0-epoch-25-avg-7-use-averaged-model.txt

@@ -0,0 +1,6 @@
+settings	WER
+no-rescore-HLG-scale-0.6	6.44
+no-rescore-HLG-scale-0.4	6.47
+no-rescore-HLG-scale-0.8	6.54
+no-rescore-HLG-scale-0.2	6.68
+no-rescore-HLG-scale-1.0	6.86

decoding_results/ctc-decoding/log-decode-epoch-25-avg-7-use-averaged-model-2022-11-27-20-36-25

@@ -0,0 +1,36 @@
+2022-11-27 20:36:25,472 INFO [decode.py:772] Decoding started
+2022-11-27 20:36:25,472 INFO [decode.py:778] Device: cuda:0
+2022-11-27 20:36:25,472 INFO [decode.py:779] {'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, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'beam_size': 10, 'reduction': 'sum', 'use_double_scores': True, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.21', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '409a24f9035df693583f9b3fea17a5934bdb3bbf', 'k2-git-date': 'Wed Nov 2 18:17:39 2022', 'lhotse-version': '1.4.0.dev+git.21b5b3f.dirty', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'latency_k2_ctc', 'icefall-git-sha1': '7817199-dirty', 'icefall-git-date': 'Tue Nov 22 20:35:37 2022', 'icefall-path': '/ceph-zw/workspace/latency/icefall_k2_ctc', 'k2-path': '/ceph-zw/workspace/latency/k2_ctc_latency/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-jb/yaozengwei/workspace/rnnt/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-2-0602201035-5fb6d86964-mclm7', 'IP address': '10.177.74.202'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'epoch': 25, 'iter': 0, 'avg': 7, 'use_averaged_model': True, 'exp_dir': PosixPath('conformer_ctc3/exp-full'), 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 0.5, 'lm_dir': PosixPath('data/my_lm'), 'simulate_streaming': False, 'decode_chunk_size': 32, 'left_context': 128, 'dynamic_chunk_training': False, 'causal_convolution': False, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank_ali'), 'max_duration': 300, '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('conformer_ctc3/exp-full/ctc-decoding'), 'suffix': 'epoch-25-avg-7-use-averaged-model'}
+2022-11-27 20:36:25,805 INFO [lexicon.py:176] Loading pre-compiled data/lang_bpe_500/Linv.pt
+2022-11-27 20:36:30,362 INFO [decode.py:865] About to create model
+2022-11-27 20:36:30,752 INFO [decode.py:932] Calculating the averaged model over epoch range from 18 (excluded) to 25
+2022-11-27 20:36:32,993 INFO [decode.py:949] Number of model parameters: 77352694
+2022-11-27 20:36:32,993 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-11-27 20:36:32,996 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-11-27 20:36:34,812 INFO [decode.py:651] batch 0/?, cuts processed until now is 23
+2022-11-27 20:37:10,536 INFO [decode.py:673] The transcripts are stored in conformer_ctc3/exp-full/ctc-decoding/recogs-test-clean-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 20:37:10,659 INFO [utils.py:731] [test-clean-ctc-decoding] %WER 3.09% [1624 / 52576, 182 ins, 111 del, 1331 sub ]
+2022-11-27 20:37:10,659 INFO [utils.py:736] [test-clean-ctc-decoding] %symbol-delay mean: 0.029s, variance: 0.003 computed on 51134 correct words
+2022-11-27 20:37:10,875 INFO [decode.py:687] Wrote detailed error stats to conformer_ctc3/exp-full/ctc-decoding/errs-test-clean-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 20:37:10,877 INFO [decode.py:717] 
+For test-clean, WER of different settings are:
+ctc-decoding	3.09	best for test-clean
+
+2022-11-27 20:37:10,877 INFO [decode.py:726] 
+For test-clean, symbol-delay of different settings are:
+ctc-decoding	mean: 0.029s, variance: 0.003	best for test-clean
+
+2022-11-27 20:37:12,170 INFO [decode.py:651] batch 0/?, cuts processed until now is 29
+2022-11-27 20:37:48,013 INFO [decode.py:673] The transcripts are stored in conformer_ctc3/exp-full/ctc-decoding/recogs-test-other-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 20:37:48,122 INFO [utils.py:731] [test-other-ctc-decoding] %WER 7.62% [3986 / 52343, 361 ins, 327 del, 3298 sub ]
+2022-11-27 20:37:48,123 INFO [utils.py:736] [test-other-ctc-decoding] %symbol-delay mean: 0.026s, variance: 0.003 computed on 48700 correct words
+2022-11-27 20:37:48,320 INFO [decode.py:687] Wrote detailed error stats to conformer_ctc3/exp-full/ctc-decoding/errs-test-other-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt
+2022-11-27 20:37:48,321 INFO [decode.py:717] 
+For test-other, WER of different settings are:
+ctc-decoding	7.62	best for test-other
+
+2022-11-27 20:37:48,321 INFO [decode.py:726] 
+For test-other, symbol-delay of different settings are:
+ctc-decoding	mean: 0.026s, variance: 0.003	best for test-other
+
+2022-11-27 20:37:48,321 INFO [decode.py:984] Done!

decoding_results/ctc-decoding/symbol-delay-summary-test-clean-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	symbol-delay
+ctc-decoding	mean: 0.029s, variance: 0.003

decoding_results/ctc-decoding/symbol-delay-summary-test-other-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	symbol-delay
+ctc-decoding	mean: 0.026s, variance: 0.003

decoding_results/ctc-decoding/wer-summary-test-clean-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+ctc-decoding	3.09

decoding_results/ctc-decoding/wer-summary-test-other-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+ctc-decoding	7.62