upload files

README.md

@@ -0,0 +1 @@
+See https://github.com/k2-fsa/icefall/pull/1766 for details

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/ctc-greedy-search/log-decode-epoch-50-avg-24-use-averaged-model-2024-09-26-10-19-26

@@ -0,0 +1,31 @@
+2024-09-26 10:19:26,383 INFO [ctc_decode_with_stats.py:784] Decoding started
+2024-09-26 10:19:26,384 INFO [ctc_decode_with_stats.py:790] Device: cuda:0
+2024-09-26 10:19:26,384 INFO [ctc_decode_with_stats.py:791] {'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, 'ignore_id': -1, 'label_smoothing': 0.1, 'warm_step': 2000, 'env_info': {'k2-version': '1.24.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '44a9d5682af9fd3ef77074777e15278ec6d390eb', 'k2-git-date': 'Wed Sep 27 11:22:55 2023', 'lhotse-version': '1.17.0.dev+git.ccfc5b2c.dirty', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'cr-ctc', 'icefall-git-sha1': 'a6eead6c-clean', 'icefall-git-date': 'Mon Sep 9 10:10:08 2024', 'icefall-path': '/star-zw/workspace/zipformer/icefall_cr_ctc', 'k2-path': '/star-zw/workspace/k2/k2/k2/python/k2/__init__.py', 'lhotse-path': '/star-zw/workspace/lhotse/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-5-0904174858-644c565fdb-d6n2c', 'IP address': '10.30.46.238'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 50, 'iter': 0, 'avg': 24, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-cr-loss-scale-0.2-time-mask-ratio-2.5-scaled-masked-1-4'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'context_size': 2, 'decoding_method': 'ctc-greedy-search', 'num_paths': 100, 'nbest_scale': 1.0, 'hlg_scale': 0.6, 'lm_dir': PosixPath('data/lm'), 'num_encoder_layers': '2,2,3,4,3,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,1024,1536,1024,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,384,512,384,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,256,256,256,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'attention_decoder_dim': 512, 'attention_decoder_num_layers': 6, 'attention_decoder_attention_dim': 512, 'attention_decoder_num_heads': 8, 'attention_decoder_feedforward_dim': 2048, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'use_transducer': False, 'use_ctc': True, 'use_attention_decoder': False, 'use_cr_ctc': True, 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank'), '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('zipformer/exp-cr-loss-scale-0.2-time-mask-ratio-2.5-scaled-masked-1-4/ctc-greedy-search'), 'suffix': 'epoch-50-avg-24-use-averaged-model'}
+2024-09-26 10:19:26,734 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_500/Linv.pt
+2024-09-26 10:19:31,369 INFO [ctc_decode_with_stats.py:876] About to create model
+2024-09-26 10:19:31,995 INFO [ctc_decode_with_stats.py:943] Calculating the averaged model over epoch range from 26 (excluded) to 50
+2024-09-26 10:19:34,611 INFO [ctc_decode_with_stats.py:960] Number of model parameters: 64250603
+2024-09-26 10:19:34,611 INFO [asr_datamodule.py:467] About to get test-clean cuts
+2024-09-26 10:19:34,748 INFO [asr_datamodule.py:474] About to get test-other cuts
+2024-09-26 10:19:35,471 INFO [ctc_decode_with_stats.py:689] batch 0/?, cuts processed until now is 21
+2024-09-26 10:19:36,831 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([5.6097, 4.6140, 5.3613, 5.0853], device='cuda:0')
+2024-09-26 10:19:45,624 INFO [ctc_decode_with_stats.py:712] The transcripts are stored in zipformer/exp-cr-loss-scale-0.2-time-mask-ratio-2.5-scaled-masked-1-4/ctc-greedy-search/recogs-test-clean-epoch-50-avg-24-use-averaged-model.txt
+2024-09-26 10:19:45,887 INFO [utils.py:657] [test-clean-ctc-greedy-search] %WER 2.12% [1116 / 52576, 113 ins, 85 del, 918 sub ]
+2024-09-26 10:19:46,101 INFO [ctc_decode_with_stats.py:721] Wrote detailed error stats to zipformer/exp-cr-loss-scale-0.2-time-mask-ratio-2.5-scaled-masked-1-4/ctc-greedy-search/errs-test-clean-epoch-50-avg-24-use-averaged-model.txt
+2024-09-26 10:19:46,106 INFO [ctc_decode_with_stats.py:735] 
+For test-clean, WER of different settings are:
+ctc-greedy-search	2.12	best for test-clean
+
+2024-09-26 10:19:46,589 INFO [ctc_decode_with_stats.py:689] batch 0/?, cuts processed until now is 26
+2024-09-26 10:19:51,927 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.3742, 3.0918, 2.6845, 2.9870], device='cuda:0')
+2024-09-26 10:19:56,892 INFO [ctc_decode_with_stats.py:712] The transcripts are stored in zipformer/exp-cr-loss-scale-0.2-time-mask-ratio-2.5-scaled-masked-1-4/ctc-greedy-search/recogs-test-other-epoch-50-avg-24-use-averaged-model.txt
+2024-09-26 10:19:57,025 INFO [utils.py:657] [test-other-ctc-greedy-search] %WER 4.62% [2416 / 52343, 235 ins, 197 del, 1984 sub ]
+2024-09-26 10:19:57,306 INFO [ctc_decode_with_stats.py:721] Wrote detailed error stats to zipformer/exp-cr-loss-scale-0.2-time-mask-ratio-2.5-scaled-masked-1-4/ctc-greedy-search/errs-test-other-epoch-50-avg-24-use-averaged-model.txt
+2024-09-26 10:19:57,312 INFO [ctc_decode_with_stats.py:735] 
+For test-other, WER of different settings are:
+ctc-greedy-search	4.62	best for test-other
+
+2024-09-26 10:19:57,313 INFO [ctc_decode_with_stats.py:1000] Averaged non-blank duration=1.284059427189012
+2024-09-26 10:19:57,317 INFO [ctc_decode_with_stats.py:1003] Averaged non-blank probs=0.8942277432591206
+2024-09-26 10:19:57,323 INFO [ctc_decode_with_stats.py:1006] Averaged blank probs=0.9419012471026017
+2024-09-26 10:19:57,323 INFO [ctc_decode_with_stats.py:1009] Done!

decoding_results/ctc-greedy-search/wer-summary-test-clean-epoch-50-avg-24-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+ctc-greedy-search	2.12

decoding_results/ctc-greedy-search/wer-summary-test-other-epoch-50-avg-24-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+ctc-greedy-search	4.62

exp/decode.sh

@@ -0,0 +1,11 @@
+export CUDA_VISIBLE_DEVICES="0"
+./zipformer/ctc_decode.py \
+  --epoch 50 \
+  --avg 24 \
+  --exp-dir zipformer/exp \
+  --use-cr-ctc 1 \
+  --use-ctc 1 \
+  --use-transducer 0 \
+  --use-attention-decoder 0 \
+  --max-duration 600 \
+  --decoding-method ctc-greedy-search

exp/epoch-50.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee8f3d4c374e465ab7619491211b5c8bc5c4171f1d7faacc02531c2aff81895
+size 1028983849

exp/export.sh

@@ -0,0 +1,10 @@
+./zipformer/export.py \
+  --exp-dir zipformer/exp \
+  --use-cr-ctc 1 \
+  --use-ctc 1 \
+  --use-transducer 0 \
+  --use-attention-decoder 0 \
+  --tokens data/lang_bpe_500/tokens.txt \
+  --epoch 50 \
+  --avg 24
+

exp/pretrained.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc69d680ce41e691ae458b1be4ff37b8330339310a356fcdf6a89228d1e46e7
+size 257406087

exp/tensorboard/events.out.tfevents.1726973457.de-74279-k2-train-7-0905180047-6d6678bc6f-8cwvw.2388799.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6986f1a061216b519b786e8d16f7ee86280b6e7f9d6082c498ac0abc8fd10090
+size 1830904

exp/train.sh

@@ -0,0 +1,17 @@
+export CUDA_VISIBLE_DEVICES="0,1,2,3"
+./zipformer/train.py \
+  --world-size 4 \
+  --num-epochs 50 \
+  --start-epoch 1 \
+  --use-fp16 1 \
+  --exp-dir zipformer/exp \
+  --use-cr-ctc 1 \
+  --use-ctc 1 \
+  --use-transducer 0 \
+  --use-attention-decoder 0 \
+  --enable-spec-aug 0 \
+  --cr-loss-scale 0.2 \
+  --time-mask-ratio 2.5 \
+  --full-libri 1 \
+  --max-duration 700 \
+  --master-port 12345