Add models and materials

README.md

@@ -0,0 +1,4 @@
+---
+license: apache-2.0
+---
+See https://github.com/k2-fsa/icefall/pull/454

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

decode_results/fast_beam_search/log-decode-epoch-25-avg-5-streaming-chunk-size-16-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2022-07-28-22-53-58

@@ -0,0 +1,25 @@
+2022-07-28 22:53:58,562 INFO [decode.py:692] Decoding started
+2022-07-28 22:53:58,563 INFO [decode.py:698] Device: cuda:0
+2022-07-28 22:53:58,566 INFO [decode.py:713] {'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, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming5', 'icefall-git-sha1': 'ee8397e-clean', 'icefall-git-date': 'Thu Jul 28 22:32:51 2022', 'icefall-path': '/ceph-kw/kangwei/code/icefall_streaming2', 'k2-path': '/ceph-hw/kangwei/code/k2_release/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-hw/kangwei/dev_tools/anaconda3/envs/rnnt2/lib/python3.8/site-packages/lhotse-1.1.0-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0616225511-78bf4545d8-tv52r', 'IP address': '10.177.77.9'}, 'epoch': 25, 'iter': 0, 'avg': 5, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L-nolinear'), '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, 'simulate_streaming': True, 'decode_chunk_size': 16, 'left_context': 32, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'dynamic_chunk_training': False, 'causal_convolution': True, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 1000, '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('pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search'), 'suffix': 'epoch-25-avg-5-streaming-chunk-size-16-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2022-07-28 22:53:58,566 INFO [decode.py:715] About to create model
+2022-07-28 22:53:59,102 INFO [decode.py:782] Calculating the averaged model over epoch range from 20 (excluded) to 25
+2022-07-28 22:54:08,088 INFO [decode.py:818] Number of model parameters: 116553580
+2022-07-28 22:54:08,089 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-07-28 22:54:08,092 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-07-28 22:54:11,600 INFO [decode.py:591] batch 0/?, cuts processed until now is 79
+2022-07-28 22:54:54,307 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:54:54,388 INFO [utils.py:416] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 3.27% [1717 / 52576, 197 ins, 118 del, 1402 sub ]
+2022-07-28 22:54:54,611 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:54:54,612 INFO [decode.py:638] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	3.27	best for test-clean
+
+2022-07-28 22:54:57,618 INFO [decode.py:591] batch 0/?, cuts processed until now is 96
+2022-07-28 22:55:41,954 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:55:42,103 INFO [utils.py:416] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 8.33% [4360 / 52343, 446 ins, 401 del, 3513 sub ]
+2022-07-28 22:55:42,337 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:55:42,337 INFO [decode.py:638] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	8.33	best for test-other
+
+2022-07-28 22:55:42,338 INFO [decode.py:847] Done!

decode_results/fast_beam_search/log-decode-epoch-25-avg-5-streaming-chunk-size-16-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2022-07-28-22-55-45

@@ -0,0 +1,25 @@
+2022-07-28 22:55:45,961 INFO [decode.py:692] Decoding started
+2022-07-28 22:55:45,962 INFO [decode.py:698] Device: cuda:0
+2022-07-28 22:55:45,965 INFO [decode.py:713] {'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, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming5', 'icefall-git-sha1': 'ee8397e-clean', 'icefall-git-date': 'Thu Jul 28 22:32:51 2022', 'icefall-path': '/ceph-kw/kangwei/code/icefall_streaming2', 'k2-path': '/ceph-hw/kangwei/code/k2_release/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-hw/kangwei/dev_tools/anaconda3/envs/rnnt2/lib/python3.8/site-packages/lhotse-1.1.0-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0616225511-78bf4545d8-tv52r', 'IP address': '10.177.77.9'}, 'epoch': 25, 'iter': 0, 'avg': 5, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L-nolinear'), '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, 'simulate_streaming': True, 'decode_chunk_size': 16, 'left_context': 64, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'dynamic_chunk_training': False, 'causal_convolution': True, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 1000, '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('pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search'), 'suffix': 'epoch-25-avg-5-streaming-chunk-size-16-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2022-07-28 22:55:45,965 INFO [decode.py:715] About to create model
+2022-07-28 22:55:46,566 INFO [decode.py:782] Calculating the averaged model over epoch range from 20 (excluded) to 25
+2022-07-28 22:55:55,578 INFO [decode.py:818] Number of model parameters: 116553580
+2022-07-28 22:55:55,578 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-07-28 22:55:55,584 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-07-28 22:55:59,378 INFO [decode.py:591] batch 0/?, cuts processed until now is 79
+2022-07-28 22:56:47,478 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:56:47,561 INFO [utils.py:416] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 3.25% [1708 / 52576, 199 ins, 120 del, 1389 sub ]
+2022-07-28 22:56:47,787 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:56:47,788 INFO [decode.py:638] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	3.25	best for test-clean
+
+2022-07-28 22:56:50,896 INFO [decode.py:591] batch 0/?, cuts processed until now is 96
+2022-07-28 22:57:34,343 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:57:34,498 INFO [utils.py:416] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 8.27% [4331 / 52343, 441 ins, 413 del, 3477 sub ]
+2022-07-28 22:57:34,731 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:57:34,732 INFO [decode.py:638] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	8.27	best for test-other
+
+2022-07-28 22:57:34,732 INFO [decode.py:847] Done!

decode_results/fast_beam_search/log-decode-epoch-25-avg-5-streaming-chunk-size-2-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2022-07-28-22-43-15

@@ -0,0 +1,25 @@
+2022-07-28 22:43:15,551 INFO [decode.py:692] Decoding started
+2022-07-28 22:43:15,552 INFO [decode.py:698] Device: cuda:0
+2022-07-28 22:43:15,555 INFO [decode.py:713] {'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, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming5', 'icefall-git-sha1': 'ee8397e-clean', 'icefall-git-date': 'Thu Jul 28 22:32:51 2022', 'icefall-path': '/ceph-kw/kangwei/code/icefall_streaming2', 'k2-path': '/ceph-hw/kangwei/code/k2_release/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-hw/kangwei/dev_tools/anaconda3/envs/rnnt2/lib/python3.8/site-packages/lhotse-1.1.0-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0616225511-78bf4545d8-tv52r', 'IP address': '10.177.77.9'}, 'epoch': 25, 'iter': 0, 'avg': 5, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L-nolinear'), '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, 'simulate_streaming': True, 'decode_chunk_size': 2, 'left_context': 32, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'dynamic_chunk_training': False, 'causal_convolution': True, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 1000, '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('pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search'), 'suffix': 'epoch-25-avg-5-streaming-chunk-size-2-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2022-07-28 22:43:15,555 INFO [decode.py:715] About to create model
+2022-07-28 22:43:16,094 INFO [decode.py:782] Calculating the averaged model over epoch range from 20 (excluded) to 25
+2022-07-28 22:43:24,055 INFO [decode.py:818] Number of model parameters: 116553580
+2022-07-28 22:43:24,056 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-07-28 22:43:24,059 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-07-28 22:43:27,503 INFO [decode.py:591] batch 0/?, cuts processed until now is 79
+2022-07-28 22:44:10,566 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-2-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:44:10,647 INFO [utils.py:416] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 3.86% [2030 / 52576, 224 ins, 160 del, 1646 sub ]
+2022-07-28 22:44:10,874 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-2-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:44:10,874 INFO [decode.py:638] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	3.86	best for test-clean
+
+2022-07-28 22:44:13,865 INFO [decode.py:591] batch 0/?, cuts processed until now is 96
+2022-07-28 22:44:58,690 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-2-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:44:58,840 INFO [utils.py:416] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 9.77% [5114 / 52343, 521 ins, 542 del, 4051 sub ]
+2022-07-28 22:44:59,075 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-2-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:44:59,075 INFO [decode.py:638] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	9.77	best for test-other
+
+2022-07-28 22:44:59,076 INFO [decode.py:847] Done!

decode_results/fast_beam_search/log-decode-epoch-25-avg-5-streaming-chunk-size-2-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2022-07-28-22-45-02

@@ -0,0 +1,25 @@
+2022-07-28 22:45:02,666 INFO [decode.py:692] Decoding started
+2022-07-28 22:45:02,666 INFO [decode.py:698] Device: cuda:0
+2022-07-28 22:45:02,669 INFO [decode.py:713] {'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, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming5', 'icefall-git-sha1': 'ee8397e-clean', 'icefall-git-date': 'Thu Jul 28 22:32:51 2022', 'icefall-path': '/ceph-kw/kangwei/code/icefall_streaming2', 'k2-path': '/ceph-hw/kangwei/code/k2_release/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-hw/kangwei/dev_tools/anaconda3/envs/rnnt2/lib/python3.8/site-packages/lhotse-1.1.0-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0616225511-78bf4545d8-tv52r', 'IP address': '10.177.77.9'}, 'epoch': 25, 'iter': 0, 'avg': 5, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L-nolinear'), '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, 'simulate_streaming': True, 'decode_chunk_size': 2, 'left_context': 64, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'dynamic_chunk_training': False, 'causal_convolution': True, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 1000, '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('pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search'), 'suffix': 'epoch-25-avg-5-streaming-chunk-size-2-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2022-07-28 22:45:02,670 INFO [decode.py:715] About to create model
+2022-07-28 22:45:03,206 INFO [decode.py:782] Calculating the averaged model over epoch range from 20 (excluded) to 25
+2022-07-28 22:45:11,168 INFO [decode.py:818] Number of model parameters: 116553580
+2022-07-28 22:45:11,168 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-07-28 22:45:11,171 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-07-28 22:45:14,576 INFO [decode.py:591] batch 0/?, cuts processed until now is 79
+2022-07-28 22:45:58,649 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-2-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:45:58,730 INFO [utils.py:416] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 3.79% [1991 / 52576, 225 ins, 148 del, 1618 sub ]
+2022-07-28 22:45:58,956 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-2-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:45:58,957 INFO [decode.py:638] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	3.79	best for test-clean
+
+2022-07-28 22:46:02,078 INFO [decode.py:591] batch 0/?, cuts processed until now is 96
+2022-07-28 22:46:45,676 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-2-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:46:45,828 INFO [utils.py:416] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 9.68% [5069 / 52343, 518 ins, 533 del, 4018 sub ]
+2022-07-28 22:46:46,074 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-2-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:46:46,075 INFO [decode.py:638] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	9.68	best for test-other
+
+2022-07-28 22:46:46,075 INFO [decode.py:847] Done!

decode_results/fast_beam_search/log-decode-epoch-25-avg-5-streaming-chunk-size-4-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2022-07-28-22-46-49

@@ -0,0 +1,25 @@
+2022-07-28 22:46:49,948 INFO [decode.py:692] Decoding started
+2022-07-28 22:46:49,948 INFO [decode.py:698] Device: cuda:0
+2022-07-28 22:46:49,952 INFO [decode.py:713] {'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, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming5', 'icefall-git-sha1': 'ee8397e-clean', 'icefall-git-date': 'Thu Jul 28 22:32:51 2022', 'icefall-path': '/ceph-kw/kangwei/code/icefall_streaming2', 'k2-path': '/ceph-hw/kangwei/code/k2_release/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-hw/kangwei/dev_tools/anaconda3/envs/rnnt2/lib/python3.8/site-packages/lhotse-1.1.0-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0616225511-78bf4545d8-tv52r', 'IP address': '10.177.77.9'}, 'epoch': 25, 'iter': 0, 'avg': 5, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L-nolinear'), '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, 'simulate_streaming': True, 'decode_chunk_size': 4, 'left_context': 32, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'dynamic_chunk_training': False, 'causal_convolution': True, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 1000, '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('pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search'), 'suffix': 'epoch-25-avg-5-streaming-chunk-size-4-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2022-07-28 22:46:49,952 INFO [decode.py:715] About to create model
+2022-07-28 22:46:50,538 INFO [decode.py:782] Calculating the averaged model over epoch range from 20 (excluded) to 25
+2022-07-28 22:46:59,606 INFO [decode.py:818] Number of model parameters: 116553580
+2022-07-28 22:46:59,606 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-07-28 22:46:59,610 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-07-28 22:47:03,048 INFO [decode.py:591] batch 0/?, cuts processed until now is 79
+2022-07-28 22:47:45,547 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-4-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:47:45,628 INFO [utils.py:416] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 3.67% [1927 / 52576, 219 ins, 157 del, 1551 sub ]
+2022-07-28 22:47:45,852 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-4-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:47:45,853 INFO [decode.py:638] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	3.67	best for test-clean
+
+2022-07-28 22:47:48,845 INFO [decode.py:591] batch 0/?, cuts processed until now is 96
+2022-07-28 22:48:30,126 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-4-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:48:30,275 INFO [utils.py:416] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 9.30% [4870 / 52343, 505 ins, 481 del, 3884 sub ]
+2022-07-28 22:48:30,512 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-4-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:48:30,513 INFO [decode.py:638] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	9.3	best for test-other
+
+2022-07-28 22:48:30,513 INFO [decode.py:847] Done!

decode_results/fast_beam_search/log-decode-epoch-25-avg-5-streaming-chunk-size-4-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2022-07-28-22-48-34

@@ -0,0 +1,25 @@
+2022-07-28 22:48:34,108 INFO [decode.py:692] Decoding started
+2022-07-28 22:48:34,108 INFO [decode.py:698] Device: cuda:0
+2022-07-28 22:48:34,111 INFO [decode.py:713] {'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, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming5', 'icefall-git-sha1': 'ee8397e-clean', 'icefall-git-date': 'Thu Jul 28 22:32:51 2022', 'icefall-path': '/ceph-kw/kangwei/code/icefall_streaming2', 'k2-path': '/ceph-hw/kangwei/code/k2_release/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-hw/kangwei/dev_tools/anaconda3/envs/rnnt2/lib/python3.8/site-packages/lhotse-1.1.0-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0616225511-78bf4545d8-tv52r', 'IP address': '10.177.77.9'}, 'epoch': 25, 'iter': 0, 'avg': 5, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L-nolinear'), '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, 'simulate_streaming': True, 'decode_chunk_size': 4, 'left_context': 64, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'dynamic_chunk_training': False, 'causal_convolution': True, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 1000, '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('pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search'), 'suffix': 'epoch-25-avg-5-streaming-chunk-size-4-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2022-07-28 22:48:34,112 INFO [decode.py:715] About to create model
+2022-07-28 22:48:34,758 INFO [decode.py:782] Calculating the averaged model over epoch range from 20 (excluded) to 25
+2022-07-28 22:48:43,664 INFO [decode.py:818] Number of model parameters: 116553580
+2022-07-28 22:48:43,664 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-07-28 22:48:43,669 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-07-28 22:48:47,298 INFO [decode.py:591] batch 0/?, cuts processed until now is 79
+2022-07-28 22:49:31,415 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-4-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:49:31,495 INFO [utils.py:416] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 3.57% [1879 / 52576, 214 ins, 147 del, 1518 sub ]
+2022-07-28 22:49:31,717 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-4-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:49:31,718 INFO [decode.py:638] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	3.57	best for test-clean
+
+2022-07-28 22:49:35,252 INFO [decode.py:591] batch 0/?, cuts processed until now is 96
+2022-07-28 22:50:23,302 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-4-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:50:23,501 INFO [utils.py:416] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 9.21% [4820 / 52343, 501 ins, 478 del, 3841 sub ]
+2022-07-28 22:50:23,746 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-4-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:50:23,747 INFO [decode.py:638] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	9.21	best for test-other
+
+2022-07-28 22:50:23,747 INFO [decode.py:847] Done!

decode_results/fast_beam_search/log-decode-epoch-25-avg-5-streaming-chunk-size-8-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2022-07-28-22-50-27

@@ -0,0 +1,25 @@
+2022-07-28 22:50:27,296 INFO [decode.py:692] Decoding started
+2022-07-28 22:50:27,296 INFO [decode.py:698] Device: cuda:0
+2022-07-28 22:50:27,300 INFO [decode.py:713] {'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, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming5', 'icefall-git-sha1': 'ee8397e-clean', 'icefall-git-date': 'Thu Jul 28 22:32:51 2022', 'icefall-path': '/ceph-kw/kangwei/code/icefall_streaming2', 'k2-path': '/ceph-hw/kangwei/code/k2_release/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-hw/kangwei/dev_tools/anaconda3/envs/rnnt2/lib/python3.8/site-packages/lhotse-1.1.0-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0616225511-78bf4545d8-tv52r', 'IP address': '10.177.77.9'}, 'epoch': 25, 'iter': 0, 'avg': 5, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L-nolinear'), '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, 'simulate_streaming': True, 'decode_chunk_size': 8, 'left_context': 32, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'dynamic_chunk_training': False, 'causal_convolution': True, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 1000, '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('pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search'), 'suffix': 'epoch-25-avg-5-streaming-chunk-size-8-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2022-07-28 22:50:27,301 INFO [decode.py:715] About to create model
+2022-07-28 22:50:27,913 INFO [decode.py:782] Calculating the averaged model over epoch range from 20 (excluded) to 25
+2022-07-28 22:50:36,879 INFO [decode.py:818] Number of model parameters: 116553580
+2022-07-28 22:50:36,879 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-07-28 22:50:36,885 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-07-28 22:50:40,308 INFO [decode.py:591] batch 0/?, cuts processed until now is 79
+2022-07-28 22:51:22,858 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-8-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:51:22,940 INFO [utils.py:416] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 3.50% [1840 / 52576, 218 ins, 137 del, 1485 sub ]
+2022-07-28 22:51:23,165 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-8-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:51:23,165 INFO [decode.py:638] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	3.5	best for test-clean
+
+2022-07-28 22:51:26,156 INFO [decode.py:591] batch 0/?, cuts processed until now is 96
+2022-07-28 22:52:07,449 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-8-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:52:07,599 INFO [utils.py:416] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 8.83% [4622 / 52343, 469 ins, 454 del, 3699 sub ]
+2022-07-28 22:52:07,834 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-8-left-context-32-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:52:07,834 INFO [decode.py:638] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	8.83	best for test-other
+
+2022-07-28 22:52:07,835 INFO [decode.py:847] Done!

decode_results/fast_beam_search/log-decode-epoch-25-avg-5-streaming-chunk-size-8-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2022-07-28-22-52-11

@@ -0,0 +1,25 @@
+2022-07-28 22:52:11,311 INFO [decode.py:692] Decoding started
+2022-07-28 22:52:11,312 INFO [decode.py:698] Device: cuda:0
+2022-07-28 22:52:11,316 INFO [decode.py:713] {'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, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming5', 'icefall-git-sha1': 'ee8397e-clean', 'icefall-git-date': 'Thu Jul 28 22:32:51 2022', 'icefall-path': '/ceph-kw/kangwei/code/icefall_streaming2', 'k2-path': '/ceph-hw/kangwei/code/k2_release/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-hw/kangwei/dev_tools/anaconda3/envs/rnnt2/lib/python3.8/site-packages/lhotse-1.1.0-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0616225511-78bf4545d8-tv52r', 'IP address': '10.177.77.9'}, 'epoch': 25, 'iter': 0, 'avg': 5, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L-nolinear'), '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, 'simulate_streaming': True, 'decode_chunk_size': 8, 'left_context': 64, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'dynamic_chunk_training': False, 'causal_convolution': True, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 1000, '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('pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search'), 'suffix': 'epoch-25-avg-5-streaming-chunk-size-8-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2022-07-28 22:52:11,316 INFO [decode.py:715] About to create model
+2022-07-28 22:52:11,896 INFO [decode.py:782] Calculating the averaged model over epoch range from 20 (excluded) to 25
+2022-07-28 22:52:20,784 INFO [decode.py:818] Number of model parameters: 116553580
+2022-07-28 22:52:20,784 INFO [asr_datamodule.py:444] About to get test-clean cuts
+2022-07-28 22:52:20,789 INFO [asr_datamodule.py:451] About to get test-other cuts
+2022-07-28 22:52:24,362 INFO [decode.py:591] batch 0/?, cuts processed until now is 79
+2022-07-28 22:53:08,214 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-8-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:53:08,296 INFO [utils.py:416] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 3.41% [1793 / 52576, 214 ins, 133 del, 1446 sub ]
+2022-07-28 22:53:08,519 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-8-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:53:08,520 INFO [decode.py:638] 
+For test-clean, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	3.41	best for test-clean
+
+2022-07-28 22:53:11,618 INFO [decode.py:591] batch 0/?, cuts processed until now is 96
+2022-07-28 22:53:54,665 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-8-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:53:54,813 INFO [utils.py:416] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 8.72% [4566 / 52343, 468 ins, 451 del, 3647 sub ]
+2022-07-28 22:53:55,047 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless5/exp-L-nolinear/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-8-left-context-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2022-07-28 22:53:55,048 INFO [decode.py:638] 
+For test-other, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	8.72	best for test-other
+
+2022-07-28 22:53:55,048 INFO [decode.py:847] Done!

decode_results/fast_beam_search/wer-summary-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-32-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	3.27

decode_results/fast_beam_search/wer-summary-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-16-left-context-64-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	3.25

decode_results/fast_beam_search/wer-summary-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-25-avg-5-streaming-chunk-size-2-left-context-32-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	3.86