initial commit

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

decoding-results/greedy_search/log-decode-epoch-30-avg-1-context-2-max-sym-per-frame-1-use-averaged-model-2023-03-21-12-56-33

@@ -0,0 +1,31 @@
+2023-03-21 12:56:33,933 INFO [decode.py:690] Decoding started
+2023-03-21 12:56:33,934 INFO [decode.py:696] Device: cuda:0
+2023-03-21 12:56:33,936 INFO [decode.py:706] {'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': '1.22', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '96c9a2aece2a3a7633da07740e24fa3d96f5498c', 'k2-git-date': 'Thu Nov 10 08:14:02 2022', 'lhotse-version': '1.13.0.dev+git.527d964.clean', 'torch-version': '1.12.1', 'torch-cuda-available': True, 'torch-cuda-version': '11.6', 'python-version': '3.8', 'icefall-git-branch': 'zipformer_libri_small_models', 'icefall-git-sha1': 'd3145cd-dirty', 'icefall-git-date': 'Thu Feb 16 15:24:55 2023', 'icefall-path': '/ceph-data4/yangxiaoyu/softwares/icefall_development/icefall_small_models', 'k2-path': '/ceph-data4/yangxiaoyu/softwares/anaconda3/envs/k2_latest/lib/python3.8/site-packages/k2/__init__.py', 'lhotse-path': '/ceph-data4/yangxiaoyu/softwares/lhotse_development/lhotse_random_padding_left/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-10-0221105906-5745685d6b-t8zzx', 'IP address': '10.177.57.19'}, 'epoch': 30, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7_streaming_multi/exp-small-6M'), '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, 'simulate_streaming': False, 'decode_chunk_size': 16, 'left_context': 64, 'num_encoder_layers': '2,2,2,2,2', 'feedforward_dims': '256,256,512,512,256', 'nhead': '4,4,4,4,4', 'encoder_dims': '128,128,128,128,128', 'attention_dims': '96,96,96,96,96', 'encoder_unmasked_dims': '96,96,96,96,96', 'zipformer_downsampling_factors': '1,2,4,8,2', 'cnn_module_kernels': '31,31,31,31,31', 'decoder_dim': 512, 'joiner_dim': 512, 'short_chunk_size': 50, 'num_left_chunks': 4, 'decode_chunk_len': 32, 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'on_the_fly_num_workers': 0, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'manifest_dir': PosixPath('data/fbank'), 'on_the_fly_feats': False, 'res_dir': PosixPath('pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search'), 'suffix': 'epoch-30-avg-1-context-2-max-sym-per-frame-1-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-03-21 12:56:33,936 INFO [decode.py:708] About to create model
+2023-03-21 12:56:34,079 INFO [zipformer.py:405] At encoder stack 4, which has downsampling_factor=2, we will combine the outputs of layers 1 and 3, with downsampling_factors=2 and 8.
+2023-03-21 12:56:34,087 INFO [train.py:536] Use giga
+2023-03-21 12:56:34,090 INFO [decode.py:779] Calculating the averaged model over epoch range from 29 (excluded) to 30
+2023-03-21 12:56:36,457 INFO [decode.py:813] Number of model parameters: 6061029
+2023-03-21 12:56:36,457 INFO [librispeech.py:58] About to get test-clean cuts from data/fbank/librispeech_cuts_test-clean.jsonl.gz
+2023-03-21 12:56:36,458 INFO [librispeech.py:63] About to get test-other cuts from data/fbank/librispeech_cuts_test-other.jsonl.gz
+2023-03-21 12:56:40,212 INFO [decode.py:592] batch 0/?, cuts processed until now is 26
+2023-03-21 12:57:18,846 INFO [decode.py:592] batch 50/?, cuts processed until now is 2526
+2023-03-21 12:57:22,546 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search/recogs-test-clean-greedy_search-epoch-30-avg-1-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-03-21 12:57:22,645 INFO [utils.py:558] [test-clean-greedy_search] %WER 6.04% [3173 / 52576, 340 ins, 306 del, 2527 sub ]
+2023-03-21 12:57:22,851 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search/errs-test-clean-greedy_search-epoch-30-avg-1-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-03-21 12:57:22,866 INFO [decode.py:637] 
+For test-clean, WER of different settings are:
+greedy_search	6.04	best for test-clean
+
+2023-03-21 12:57:24,870 INFO [decode.py:592] batch 0/?, cuts processed until now is 30
+2023-03-21 12:57:29,066 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.3041, 1.5690, 1.5069, 1.2777], device='cuda:0'), covar=tensor([0.2984, 0.2516, 0.1772, 0.2404], device='cuda:0'), in_proj_covar=tensor([0.2077, 0.2042, 0.1947, 0.2094], device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002], device='cuda:0')
+2023-03-21 12:57:56,255 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.2700, 1.9217, 1.5033, 0.4634], device='cuda:0'), covar=tensor([0.4861, 0.3328, 0.4618, 0.7099], device='cuda:0'), in_proj_covar=tensor([0.1863, 0.1746, 0.1668, 0.1515], device='cuda:0'), out_proj_covar=tensor([0.0005, 0.0005, 0.0004, 0.0004], device='cuda:0')
+2023-03-21 12:57:59,184 INFO [decode.py:592] batch 50/?, cuts processed until now is 2840
+2023-03-21 12:58:02,446 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search/recogs-test-other-greedy_search-epoch-30-avg-1-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-03-21 12:58:02,551 INFO [utils.py:558] [test-other-greedy_search] %WER 15.06% [7882 / 52343, 827 ins, 900 del, 6155 sub ]
+2023-03-21 12:58:02,776 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search/errs-test-other-greedy_search-epoch-30-avg-1-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-03-21 12:58:02,776 INFO [decode.py:637] 
+For test-other, WER of different settings are:
+greedy_search	15.06	best for test-other
+
+2023-03-21 12:58:02,777 INFO [decode.py:845] Done!

decoding-results/greedy_search/log-decode-epoch-30-avg-10-context-2-max-sym-per-frame-1-use-averaged-model-2023-03-21-12-42-29

@@ -0,0 +1,31 @@
+2023-03-21 12:42:29,212 INFO [decode.py:690] Decoding started
+2023-03-21 12:42:29,212 INFO [decode.py:696] Device: cuda:0
+2023-03-21 12:42:29,235 INFO [decode.py:706] {'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': '1.22', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '96c9a2aece2a3a7633da07740e24fa3d96f5498c', 'k2-git-date': 'Thu Nov 10 08:14:02 2022', 'lhotse-version': '1.13.0.dev+git.527d964.clean', 'torch-version': '1.12.1', 'torch-cuda-available': True, 'torch-cuda-version': '11.6', 'python-version': '3.8', 'icefall-git-branch': 'zipformer_libri_small_models', 'icefall-git-sha1': 'd3145cd-dirty', 'icefall-git-date': 'Thu Feb 16 15:24:55 2023', 'icefall-path': '/ceph-data4/yangxiaoyu/softwares/icefall_development/icefall_small_models', 'k2-path': '/ceph-data4/yangxiaoyu/softwares/anaconda3/envs/k2_latest/lib/python3.8/site-packages/k2/__init__.py', 'lhotse-path': '/ceph-data4/yangxiaoyu/softwares/lhotse_development/lhotse_random_padding_left/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-10-0221105906-5745685d6b-t8zzx', 'IP address': '10.177.57.19'}, 'epoch': 30, 'iter': 0, 'avg': 10, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7_streaming_multi/exp-small-6M'), '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, 'simulate_streaming': False, 'decode_chunk_size': 16, 'left_context': 64, 'num_encoder_layers': '2,2,2,2,2', 'feedforward_dims': '256,256,512,512,256', 'nhead': '4,4,4,4,4', 'encoder_dims': '128,128,128,128,128', 'attention_dims': '96,96,96,96,96', 'encoder_unmasked_dims': '96,96,96,96,96', 'zipformer_downsampling_factors': '1,2,4,8,2', 'cnn_module_kernels': '31,31,31,31,31', 'decoder_dim': 512, 'joiner_dim': 512, 'short_chunk_size': 50, 'num_left_chunks': 4, 'decode_chunk_len': 32, 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'on_the_fly_num_workers': 0, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'manifest_dir': PosixPath('data/fbank'), 'on_the_fly_feats': False, 'res_dir': PosixPath('pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search'), 'suffix': 'epoch-30-avg-10-context-2-max-sym-per-frame-1-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-03-21 12:42:29,235 INFO [decode.py:708] About to create model
+2023-03-21 12:42:29,390 INFO [zipformer.py:405] At encoder stack 4, which has downsampling_factor=2, we will combine the outputs of layers 1 and 3, with downsampling_factors=2 and 8.
+2023-03-21 12:42:29,398 INFO [train.py:536] Use giga
+2023-03-21 12:42:29,401 INFO [decode.py:779] Calculating the averaged model over epoch range from 20 (excluded) to 30
+2023-03-21 12:42:31,968 INFO [decode.py:813] Number of model parameters: 6061029
+2023-03-21 12:42:31,968 INFO [librispeech.py:58] About to get test-clean cuts from data/fbank/librispeech_cuts_test-clean.jsonl.gz
+2023-03-21 12:42:31,977 INFO [librispeech.py:63] About to get test-other cuts from data/fbank/librispeech_cuts_test-other.jsonl.gz
+2023-03-21 12:42:35,929 INFO [decode.py:592] batch 0/?, cuts processed until now is 26
+2023-03-21 12:43:11,716 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.0073, 1.5345, 1.5496, 1.3240], device='cuda:0'), covar=tensor([0.2695, 0.1998, 0.2626, 0.2169], device='cuda:0'), in_proj_covar=tensor([0.0488, 0.0749, 0.0718, 0.0687], device='cuda:0'), out_proj_covar=tensor([0.0007, 0.0010, 0.0010, 0.0009], device='cuda:0')
+2023-03-21 12:43:13,944 INFO [decode.py:592] batch 50/?, cuts processed until now is 2526
+2023-03-21 12:43:17,637 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search/recogs-test-clean-greedy_search-epoch-30-avg-10-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-03-21 12:43:17,736 INFO [utils.py:558] [test-clean-greedy_search] %WER 6.11% [3215 / 52576, 343 ins, 302 del, 2570 sub ]
+2023-03-21 12:43:17,965 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search/errs-test-clean-greedy_search-epoch-30-avg-10-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-03-21 12:43:17,966 INFO [decode.py:637] 
+For test-clean, WER of different settings are:
+greedy_search	6.11	best for test-clean
+
+2023-03-21 12:43:20,725 INFO [decode.py:592] batch 0/?, cuts processed until now is 30
+2023-03-21 12:43:58,180 INFO [decode.py:592] batch 50/?, cuts processed until now is 2840
+2023-03-21 12:43:59,263 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.4355, 1.8449, 1.4393, 1.3780], device='cuda:0'), covar=tensor([0.3140, 0.2956, 0.3352, 0.2758], device='cuda:0'), in_proj_covar=tensor([0.1560, 0.1123, 0.1377, 0.1001], device='cuda:0'), out_proj_covar=tensor([0.0014, 0.0012, 0.0013, 0.0009], device='cuda:0')
+2023-03-21 12:44:02,632 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search/recogs-test-other-greedy_search-epoch-30-avg-10-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-03-21 12:44:02,732 INFO [utils.py:558] [test-other-greedy_search] %WER 15.28% [7998 / 52343, 819 ins, 936 del, 6243 sub ]
+2023-03-21 12:44:02,954 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless7_streaming_multi/exp-small-6M/greedy_search/errs-test-other-greedy_search-epoch-30-avg-10-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-03-21 12:44:02,955 INFO [decode.py:637] 
+For test-other, WER of different settings are:
+greedy_search	15.28	best for test-other
+
+2023-03-21 12:44:02,955 INFO [decode.py:845] Done!

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

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search	6.04

decoding-results/greedy_search/wer-summary-test-clean-greedy_search-epoch-30-avg-10-context-2-max-sym-per-frame-1-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search	6.11

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

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search	15.06

decoding-results/greedy_search/wer-summary-test-other-greedy_search-epoch-30-avg-10-context-2-max-sym-per-frame-1-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search	15.28

decoding-results/modified_beam_search/log-decode-epoch-30-avg-1-modified_beam_search-beam-size-4-use-averaged-model-2023-03-21-13-44-53

@@ -0,0 +1,34 @@
+2023-03-21 13:44:53,273 INFO [decode.py:690] Decoding started
+2023-03-21 13:44:53,274 INFO [decode.py:696] Device: cuda:0
+2023-03-21 13:44:53,281 INFO [decode.py:706] {'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': '1.22', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '96c9a2aece2a3a7633da07740e24fa3d96f5498c', 'k2-git-date': 'Thu Nov 10 08:14:02 2022', 'lhotse-version': '1.13.0.dev+git.527d964.clean', 'torch-version': '1.12.1', 'torch-cuda-available': True, 'torch-cuda-version': '11.6', 'python-version': '3.8', 'icefall-git-branch': 'zipformer_libri_small_models', 'icefall-git-sha1': 'd3145cd-dirty', 'icefall-git-date': 'Thu Feb 16 15:24:55 2023', 'icefall-path': '/ceph-data4/yangxiaoyu/softwares/icefall_development/icefall_small_models', 'k2-path': '/ceph-data4/yangxiaoyu/softwares/anaconda3/envs/k2_latest/lib/python3.8/site-packages/k2/__init__.py', 'lhotse-path': '/ceph-data4/yangxiaoyu/softwares/lhotse_development/lhotse_random_padding_left/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-10-0221105906-5745685d6b-t8zzx', 'IP address': '10.177.57.19'}, 'epoch': 30, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7_streaming_multi/exp-small-6M'), '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, 'simulate_streaming': False, 'decode_chunk_size': 16, 'left_context': 64, 'num_encoder_layers': '2,2,2,2,2', 'feedforward_dims': '256,256,512,512,256', 'nhead': '4,4,4,4,4', 'encoder_dims': '128,128,128,128,128', 'attention_dims': '96,96,96,96,96', 'encoder_unmasked_dims': '96,96,96,96,96', 'zipformer_downsampling_factors': '1,2,4,8,2', 'cnn_module_kernels': '31,31,31,31,31', 'decoder_dim': 512, 'joiner_dim': 512, 'short_chunk_size': 50, 'num_left_chunks': 4, 'decode_chunk_len': 32, 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'on_the_fly_num_workers': 0, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'manifest_dir': PosixPath('data/fbank'), 'on_the_fly_feats': False, 'res_dir': PosixPath('pruned_transducer_stateless7_streaming_multi/exp-small-6M/modified_beam_search'), 'suffix': 'epoch-30-avg-1-modified_beam_search-beam-size-4-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-03-21 13:44:53,281 INFO [decode.py:708] About to create model
+2023-03-21 13:44:53,427 INFO [zipformer.py:405] At encoder stack 4, which has downsampling_factor=2, we will combine the outputs of layers 1 and 3, with downsampling_factors=2 and 8.
+2023-03-21 13:44:53,435 INFO [train.py:536] Use giga
+2023-03-21 13:44:53,438 INFO [decode.py:779] Calculating the averaged model over epoch range from 29 (excluded) to 30
+2023-03-21 13:44:55,938 INFO [decode.py:813] Number of model parameters: 6061029
+2023-03-21 13:44:55,938 INFO [librispeech.py:58] About to get test-clean cuts from data/fbank/librispeech_cuts_test-clean.jsonl.gz
+2023-03-21 13:44:55,947 INFO [librispeech.py:63] About to get test-other cuts from data/fbank/librispeech_cuts_test-other.jsonl.gz
+2023-03-21 13:45:03,046 INFO [decode.py:592] batch 0/?, cuts processed until now is 26
+2023-03-21 13:46:18,846 INFO [decode.py:592] batch 20/?, cuts processed until now is 1545
+2023-03-21 13:47:05,883 INFO [decode.py:592] batch 40/?, cuts processed until now is 2375
+2023-03-21 13:47:07,579 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.4154, 1.2778, 1.1482, 1.5772], device='cuda:0'), covar=tensor([0.0857, 0.0405, 0.0402, 0.0997], device='cuda:0'), in_proj_covar=tensor([0.0195, 0.0123, 0.0121, 0.0232], device='cuda:0'), out_proj_covar=tensor([0.0107, 0.0076, 0.0067, 0.0117], device='cuda:0')
+2023-03-21 13:47:32,569 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless7_streaming_multi/exp-small-6M/modified_beam_search/recogs-test-clean-beam_size_4-epoch-30-avg-1-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-03-21 13:47:32,668 INFO [utils.py:558] [test-clean-beam_size_4] %WER 5.79% [3044 / 52576, 344 ins, 283 del, 2417 sub ]
+2023-03-21 13:47:32,999 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless7_streaming_multi/exp-small-6M/modified_beam_search/errs-test-clean-beam_size_4-epoch-30-avg-1-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-03-21 13:47:33,006 INFO [decode.py:637] 
+For test-clean, WER of different settings are:
+beam_size_4	5.79	best for test-clean
+
+2023-03-21 13:47:38,189 INFO [decode.py:592] batch 0/?, cuts processed until now is 30
+2023-03-21 13:47:52,805 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.2750, 1.3069, 3.4282, 3.1751], device='cuda:0'), covar=tensor([0.1717, 0.2875, 0.0558, 0.0988], device='cuda:0'), in_proj_covar=tensor([0.0816, 0.0679, 0.1016, 0.0992], device='cuda:0'), out_proj_covar=tensor([0.0011, 0.0010, 0.0011, 0.0012], device='cuda:0')
+2023-03-21 13:48:55,576 INFO [decode.py:592] batch 20/?, cuts processed until now is 1771
+2023-03-21 13:49:08,575 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.2201, 1.2812, 3.5021, 3.1816], device='cuda:0'), covar=tensor([0.1809, 0.2933, 0.0553, 0.1024], device='cuda:0'), in_proj_covar=tensor([0.0816, 0.0679, 0.1016, 0.0992], device='cuda:0'), out_proj_covar=tensor([0.0011, 0.0010, 0.0011, 0.0012], device='cuda:0')
+2023-03-21 13:49:39,149 INFO [decode.py:592] batch 40/?, cuts processed until now is 2696
+2023-03-21 13:50:02,629 INFO [decode.py:608] The transcripts are stored in pruned_transducer_stateless7_streaming_multi/exp-small-6M/modified_beam_search/recogs-test-other-beam_size_4-epoch-30-avg-1-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-03-21 13:50:02,738 INFO [utils.py:558] [test-other-beam_size_4] %WER 14.38% [7525 / 52343, 869 ins, 749 del, 5907 sub ]
+2023-03-21 13:50:02,957 INFO [decode.py:621] Wrote detailed error stats to pruned_transducer_stateless7_streaming_multi/exp-small-6M/modified_beam_search/errs-test-other-beam_size_4-epoch-30-avg-1-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-03-21 13:50:02,958 INFO [decode.py:637] 
+For test-other, WER of different settings are:
+beam_size_4	14.38	best for test-other
+
+2023-03-21 13:50:02,958 INFO [decode.py:845] Done!

decoding-results/modified_beam_search/wer-summary-test-clean-beam_size_4-epoch-30-avg-1-modified_beam_search-beam-size-4-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_size_4	5.79

decoding-results/modified_beam_search/wer-summary-test-other-beam_size_4-epoch-30-avg-1-modified_beam_search-beam-size-4-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_size_4	14.38

exp/cpu_jit.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f74e62d8f0190a79c4de28f39b08b19d9cba9cae2d3332c651ea1489c80fe12
+size 50059462

exp/epoch-30.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a338ace5aacba9a8351d257f904f6514583665fb513e83ad0a7794fa3b8285
+size 97434465

exp/pretrained-epoch-30-avg-1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32b64dca464a97f79b025b43c0b6442f726b8f816fc1d5f8c242af6b347b600
+size 24440027

exp/tensorboard/events.out.tfevents.1677551914.de-74279-k2-train-2-1216192652-5bcf7587b4-n6q9m.65872.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013ae7fb82a1637bb90f74e8ce175e5baaca880ad5167075027eb48e6479366a
+size 28462708

test_wavs/trans.txt

@@ -0,0 +1,3 @@
+1089-134686-0001 AFTER EARLY NIGHTFALL THE YELLOW LAMPS WOULD LIGHT UP HERE AND THERE THE SQUALID QUARTER OF THE BROTHELS
+1221-135766-0001 GOD AS A DIRECT CONSEQUENCE OF THE SIN WHICH MAN THUS PUNISHED HAD GIVEN HER A LOVELY CHILD WHOSE PLACE WAS ON THAT SAME DISHONOURED BOSOM TO CONNECT HER PARENT FOR EVER WITH THE RACE AND DESCENT OF MORTALS AND TO BE FINALLY A BLESSED SOUL IN HEAVEN
+1221-135766-0002 YET THESE THOUGHTS AFFECTED HESTER PRYNNE LESS WITH HOPE THAN APPREHENSION