Upload 34 files

.gitattributes

@@ -32,3 +32,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/lang_bpe_500/L_disambig.fst filter=lfs diff=lfs merge=lfs -text
+data/lang_bpe_500/L.fst filter=lfs diff=lfs merge=lfs -text
+data/lang_bpe_500/train_orig.txt filter=lfs diff=lfs merge=lfs -text
+data/lang_bpe_500/train.txt filter=lfs diff=lfs merge=lfs -text
+data/lm/3gram.arpa filter=lfs diff=lfs merge=lfs -text
+data/lm/4gram.arpa filter=lfs diff=lfs merge=lfs -text
+data/lm/G_3_gram.fst.txt filter=lfs diff=lfs merge=lfs -text
+data/lm/G_4_gram.fst.txt filter=lfs diff=lfs merge=lfs -text

data/lang_bpe_500/HLG.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1431e9712ce1bf45a3e8ad9775eb148306298a96ed9a642c75be50ab0566da55
+size 1091845447

data/lang_bpe_500/L.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70de241a0a4b31867f12d84a2c7f61920df2cd3a09c321da1367c8abd95a820e
+size 20698447

data/lang_bpe_500/LG.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f0f73fcd23cd1c17650c87bb70bc4da56f98977105bed69fe1deb91989b37b
+size 306392522

data/lang_bpe_500/L_disambig.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6787b0bc4a08f369d364e4b475a29c7f6d49a0d81e881daaf1468c832bd01cd1
+size 21392435

data/lang_bpe_500/Linv.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6e66b8d4f763b913ebafd0f21dfe374549df05d704e6587cfb27050bcfc82c
+size 20698459

data/lang_bpe_500/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787932caf5c0adf93e850c18742279142ab33cdff5a6bd1234ad3aca2fc0b998
+size 244624

data/lang_bpe_500/tokens.txt

@@ -0,0 +1,502 @@
+<blk> 0
+<sos/eos> 1
+<unk> 2
+S 3
+▁ 4
+E 5
+▁DE 6
+' 7
+T 8
+R 9
+É 10
+▁L 11
+▁LA 12
+C 13
+▁LE 14
+A 15
+O 16
+P 17
+▁D 18
+U 19
+I 20
+▁EST 21
+▁IL 22
+ON 23
+N 24
+▁À 25
+▁S 26
+▁A 27
+▁ET 28
+▁C 29
+IN 30
+D 31
+G 32
+ER 33
+ES 34
+▁EN 35
+▁LES 36
+Y 37
+IS 38
+IT 39
+L 40
+▁DU 41
+AL 42
+ENT 43
+▁F 44
+RE 45
+▁PAR 46
+▁DES 47
+F 48
+LE 49
+▁UN 50
+▁B 51
+▁SE 52
+V 53
+▁AU 54
+AN 55
+B 56
+OR 57
+▁G 58
+RA 59
+ANT 60
+OU 61
+H 62
+UR 63
+▁DANS 64
+▁T 65
+RI 66
+▁M 67
+TE 68
+▁RE 69
+AR 70
+▁UNE 71
+▁ELLE 72
+▁V 73
+M 74
+ATION 75
+UL 76
+ÉE 77
+Z 78
+▁N 79
+NE 80
+ME 81
+IL 82
+▁P 83
+MENT 84
+IE 85
+EN 86
+▁H 87
+▁CON 88
+IR 89
+EST 90
+LI 91
+▁SON 92
+CH 93
+▁POUR 94
+È 95
+LA 96
+CE 97
+▁RÉ 98
+▁MA 99
+IQUE 100
+▁CE 101
+EUR 102
+▁SA 103
+NT 104
+▁SONT 105
+US 106
+EMENT 107
+▁IN 108
+▁PRO 109
+▁SUR 110
+RÉ 111
+RO 112
+▁DÉ 113
+AIT 114
+DE 115
+▁QU 116
+▁É 117
+EL 118
+OL 119
+AIRE 120
+ION 121
+UN 122
+CHE 123
+K 124
+▁CH 125
+AT 126
+DI 127
+AG 128
+TRE 129
+TI 130
+OM 131
+ELLE 132
+▁SU 133
+AM 134
+▁PO 135
+▁MO 136
+IM 137
+▁PAS 138
+VI 139
+TÉ 140
+FF 141
+▁CA 142
+TER 143
+END 144
+CETTE 145
+QUE 146
+TA 147
+LO 148
+▁PLUS 149
+ILLE 150
+QU 151
+▁NE 152
+▁RO 153
+▁JE 154
+▁QUE 155
+▁DEUX 156
+UT 157
+CI 158
+ALE 159
+▁AVEC 160
+UNE 161
+AB 162
+ITÉ 163
+IC 164
+GE 165
+MA 166
+AGE 167
+AND 168
+AC 169
+OIS 170
+▁CO 171
+▁COMME 172
+PH 173
+VER 174
+SSE 175
+AV 176
+▁QUI 177
+TU 178
+▁BA 179
+NÉ 180
+ID 181
+PORT 182
+▁VO 183
+IER 184
+▁ÉTÉ 185
+MI 186
+IV 187
+ÈRE 188
+ARD 189
+AU 190
+OC 191
+▁EX 192
+▁DI 193
+▁CHA 194
+ÉRI 195
+MB 196
+IGN 197
+▁RA 198
+DU 199
+ISTE 200
+TH 201
+AIS 202
+INE 203
+ANG 204
+▁COMP 205
+▁OU 206
+AUX 207
+IÈRE 208
+ORD 209
+X 210
+▁PR 211
+▁ÉGALEMENT 212
+▁CONS 213
+LU 214
+▁SES 215
+▁SOU 216
+POS 217
+CTION 218
+NA 219
+TO 220
+OUR 221
+ART 222
+Ô 223
+UE 224
+MÉ 225
+TION 226
+▁NOM 227
+▁MAR 228
+AS 229
+MAN 230
+LÉ 231
+ILL 232
+▁COM 233
+▁PA 234
+W 235
+TURE 236
+MIN 237
+▁MAIS 238
+VE 239
+ITE 240
+IX 241
+ANCE 242
+ENCE 243
+OP 244
+EMP 245
+ALL 246
+EUX 247
+▁K 248
+▁ÉTAIT 249
+▁FAIT 250
+J 251
+▁TOUT 252
+TIQUE 253
+PE 254
+UV 255
+▁PLA 256
+IRE 257
+ENS 258
+▁Y 259
+IG 260
+VO 261
+VEN 262
+ABLE 263
+▁AUX 264
+▁MON 265
+ÊT 266
+▁AUSSI 267
+▁FOR 268
+TRA 269
+LES 270
+NI 271
+TRI 272
+▁DIS 273
+▁MI 274
+▁TRA 275
+▁CENT 276
+▁TO 277
+ÉS 278
+TTE 279
+EX 280
+▁APP 281
+▁GRAND 282
+▁AR 283
+INS 284
+▁NO 285
+▁DÉC 286
+MO 287
+▁BR 288
+▁AN 289
+ÉES 290
+ONNE 291
+▁PRÉ 292
+▁ME 293
+▁LUI 294
+▁FA 295
+TEN 296
+AUT 297
+BL 298
+IVE 299
+Ç 300
+Â 301
+▁FUT 302
+▁SO 303
+▁TROIS 304
+EAU 305
+▁ALORS 306
+TEUR 307
+▁MÉ 308
+DA 309
+▁J 310
+▁ON 311
+▁JA 312
+GUE 313
+▁LEUR 314
+ÈME 315
+▁ONT 316
+▁W 317
+▁MÊME 318
+ACC 319
+IEN 320
+▁SAINT 321
+AINE 322
+À 323
+▁VA 324
+▁FIN 325
+ICI 326
+ITION 327
+▁CES 328
+▁COUR 329
+UM 330
+BRE 331
+▁PEU 332
+Î 333
+TRO 334
+IENNE 335
+IDE 336
+▁REP 337
+▁JU 338
+▁VILLE 339
+▁APRÈS 340
+▁ÊTRE 341
+▁RI 342
+▁VOUS 343
+▁PLUSIEURS 344
+▁NA 345
+▁TH 346
+ANTE 347
+TRÈS 348
+▁SITUÉ 349
+▁TOUR 350
+▁PARTIE 351
+▁FRANC 352
+▁QUATRE 353
+▁PER 354
+VIENT 355
+▁ENTRE 356
+ING 357
+▁PREMIER 358
+▁CAR 359
+LON 360
+FORM 361
+BA 362
+VÉ 363
+IFI 364
+AIENT 365
+HI 366
+▁JO 367
+TIF 368
+TANT 369
+▁PEUT 370
+STRU 371
+▁PARTI 372
+▁COMMUNE 373
+Ê 374
+▁REN 375
+ATEUR 376
+▁BIEN 377
+▁PRI 378
+▁RUE 379
+▁MONT 380
+▁PI 381
+▁JOUR 382
+AUTRES 383
+IBLE 384
+APP 385
+▁CINQ 386
+▁PREMIÈRE 387
+▁MARI 388
+CK 389
+▁TROUVE 390
+ISSE 391
+▁DONC 392
+▁GROUPE 393
+▁JOUE 394
+▁VERS 395
+JO 396
+ÎT 397
+ÉTAT 398
+▁FRANÇAIS 399
+▁LORS 400
+▁ENSUITE 401
+▁PUIS 402
+▁PETIT 403
+EUSE 404
+▁AINSI 405
+▁TRAVAIL 406
+▁NOUS 407
+▁QUELQUE 408
+▁COLL 409
+▁CERTAIN 410
+▁LIEU 411
+▁PRÉSENT 412
+ÉQUIPE 413
+▁VINGT 414
+▁PÈRE 415
+▁FAMILLE 416
+▁RU 417
+▁RENCONTRE 418
+▁ESPÈCE 419
+▁FILS 420
+▁GÉNÉRAL 421
+▁OB 422
+▁ÉV 423
+Ï 424
+▁PAYS 425
+▁ANNÉE 426
+ÉGLISE 427
+▁PRINCIPAL 428
+▁GUERRE 429
+▁SANS 430
+ANCIEN 431
+▁CEPENDANT 432
+▁RESTE 433
+Π434
+▁PENDANT 435
+▁TEMPS 436
+▁FOND 437
+HUI 438
+▁RÉGION 439
+MM 440
+▁MEMBRE 441
+Û 442
+▁TRANS 443
+▁CLUB 444
+BERT 445
+▁DEPUIS 446
+▁IMP 447
+PRÈS 448
+▁SEPT 449
+▁NATIONAL 450
+▁CONNU 451
+▁VILLAGE 452
+▁MORT 453
+▁ENCORE 454
+ORGANIS 455
+HISTOIRE 456
+Ù 457
+▁SECOND 458
+▁NOUVELLE 459
+ŒUVRE 460
+ORIGINE 461
+UNIVERSITÉ 462
+▁UTILISÉ 463
+▁AUJOURD 464
+▁COMMUN 465
+▁FILM 466
+▁FRÈRE 467
+▁TITRE 468
+▁DIRECT 469
+ÉLECT 470
+▁FEMME 471
+▁HUIT 472
+ÉTAIENT 473
+ÉCOLE 474
+▁DERNIER 475
+▁MONSIEUR 476
+▁IMPORTANT 477
+▁PERMET 478
+▁JUSQU 479
+▁DROIT 480
+▁CARRIÈRE 481
+ARCHI 482
+▁NOMBREUX 483
+▁SAISON 484
+▁NOTAMMENT 485
+▁PIERRE 486
+BOURG 487
+▁DIFFÉRENT 488
+▁NOUVEAU 489
+▁TOUJOURS 490
+▁SIÈGE 491
+ÉDIT 492
+▁PERSONNE 493
+▁SUIVANT 494
+▁CELUI 495
+Ë 496
+Ü 497
+Q 498
+Æ 499
+#0 500
+#1 501

data/lang_bpe_500/train.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279dd4ab74b7c19c20543f31660564cb4dc2adddc4097356f22782928fd76ecd
+size 31024469

data/lang_bpe_500/train_orig.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8868efaf3b191da9546ec193cbb0788a847b52b07d7a0c6ecedf0e07dda19c2b
+size 32593161

data/lang_bpe_500/unigram_500.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787932caf5c0adf93e850c18742279142ab33cdff5a6bd1234ad3aca2fc0b998
+size 244624

data/lang_bpe_500/unigram_500.vocab

@@ -0,0 +1,500 @@
+<blk>	0
+<sos/eos>	0
+<unk>	0
+S	-2.95044
+▁	-3.52819
+E	-3.61069
+▁DE	-3.77593
+'	-3.80476
+T	-3.98568
+R	-4.21426
+É	-4.21489
+▁L	-4.24855
+▁LA	-4.30356
+C	-4.37675
+▁LE	-4.50794
+A	-4.51183
+O	-4.52633
+P	-4.53401
+▁D	-4.54343
+U	-4.57523
+I	-4.57714
+▁EST	-4.70374
+▁IL	-4.72016
+ON	-4.78236
+N	-4.81209
+▁À	-4.8331
+▁S	-4.86694
+▁A	-4.86931
+▁ET	-4.90966
+▁C	-4.93591
+IN	-4.96857
+D	-4.97671
+G	-5.00877
+ER	-5.02622
+ES	-5.05635
+▁EN	-5.07399
+▁LES	-5.12278
+Y	-5.12281
+IS	-5.12371
+IT	-5.1512
+L	-5.2095
+▁DU	-5.27551
+AL	-5.30047
+ENT	-5.32252
+▁F	-5.32693
+RE	-5.34073
+▁PAR	-5.34309
+▁DES	-5.37599
+F	-5.40391
+LE	-5.41817
+▁UN	-5.4263
+▁B	-5.42928
+▁SE	-5.45833
+V	-5.4948
+▁AU	-5.51091
+AN	-5.51095
+B	-5.52945
+OR	-5.57706
+▁G	-5.59256
+RA	-5.60306
+ANT	-5.61866
+OU	-5.62585
+H	-5.63579
+UR	-5.65002
+▁DANS	-5.65339
+▁T	-5.65478
+RI	-5.66107
+▁M	-5.67156
+TE	-5.68258
+▁RE	-5.70332
+AR	-5.71733
+▁UNE	-5.73579
+▁ELLE	-5.73837
+▁V	-5.77157
+M	-5.80446
+ATION	-5.80592
+UL	-5.82578
+ÉE	-5.83786
+Z	-5.84404
+▁N	-5.85083
+NE	-5.85186
+ME	-5.85253
+IL	-5.85976
+▁P	-5.8625
+MENT	-5.86255
+IE	-5.87153
+EN	-5.87781
+▁H	-5.87931
+▁CON	-5.91114
+IR	-5.92419
+EST	-5.9346
+LI	-5.93858
+▁SON	-5.94037
+CH	-5.94997
+▁POUR	-5.95025
+È	-5.97227
+LA	-5.98258
+CE	-6.00354
+▁RÉ	-6.00832
+▁MA	-6.01047
+IQUE	-6.01627
+▁CE	-6.01653
+EUR	-6.0238
+▁SA	-6.03806
+NT	-6.09711
+▁SONT	-6.09794
+US	-6.10094
+EMENT	-6.1151
+▁IN	-6.12361
+▁PRO	-6.12491
+▁SUR	-6.14045
+RÉ	-6.14134
+RO	-6.14433
+▁DÉ	-6.14668
+AIT	-6.14836
+DE	-6.15261
+▁QU	-6.15573
+▁É	-6.15607
+EL	-6.15758
+OL	-6.15966
+AIRE	-6.17272
+ION	-6.17315
+UN	-6.17769
+CHE	-6.18594
+K	-6.22088
+▁CH	-6.22102
+AT	-6.25802
+DI	-6.2675
+AG	-6.28667
+TRE	-6.28903
+TI	-6.29845
+OM	-6.31474
+ELLE	-6.32241
+▁SU	-6.3278
+AM	-6.3377
+▁PO	-6.33994
+▁MO	-6.3488
+IM	-6.35296
+▁PAS	-6.35478
+VI	-6.37582
+TÉ	-6.39092
+FF	-6.39812
+▁CA	-6.40222
+TER	-6.40368
+END	-6.40953
+CETTE	-6.41276
+QUE	-6.41398
+TA	-6.41647
+LO	-6.42665
+▁PLUS	-6.43945
+ILLE	-6.44629
+QU	-6.47038
+▁NE	-6.5018
+▁RO	-6.51476
+▁JE	-6.52588
+▁QUE	-6.53357
+▁DEUX	-6.54569
+UT	-6.56102
+CI	-6.56669
+ALE	-6.5754
+▁AVEC	-6.57591
+UNE	-6.58781
+AB	-6.59318
+ITÉ	-6.59338
+IC	-6.59991
+GE	-6.60459
+MA	-6.61775
+AGE	-6.61823
+AND	-6.62569
+AC	-6.63217
+OIS	-6.6338
+▁CO	-6.645
+▁COMME	-6.65494
+PH	-6.65508
+VER	-6.6556
+SSE	-6.66542
+AV	-6.67119
+▁QUI	-6.67297
+TU	-6.68589
+▁BA	-6.68726
+NÉ	-6.69021
+ID	-6.69194
+PORT	-6.70656
+▁VO	-6.71041
+IER	-6.71949
+▁ÉTÉ	-6.74721
+MI	-6.74758
+IV	-6.74785
+ÈRE	-6.75787
+ARD	-6.76178
+AU	-6.76538
+OC	-6.77933
+▁EX	-6.7813
+▁DI	-6.79024
+▁CHA	-6.79452
+ÉRI	-6.79873
+MB	-6.82177
+IGN	-6.82265
+▁RA	-6.82444
+DU	-6.8371
+ISTE	-6.83906
+TH	-6.84131
+AIS	-6.84576
+INE	-6.8465
+ANG	-6.84672
+▁COMP	-6.85555
+▁OU	-6.85622
+AUX	-6.86386
+IÈRE	-6.86924
+ORD	-6.86985
+X	-6.87628
+▁PR	-6.87928
+▁ÉGALEMENT	-6.88091
+▁CONS	-6.88205
+LU	-6.88394
+▁SES	-6.88761
+▁SOU	-6.89325
+POS	-6.89602
+CTION	-6.89668
+NA	-6.90352
+TO	-6.90354
+OUR	-6.90604
+ART	-6.91586
+Ô	-6.91748
+UE	-6.92409
+MÉ	-6.94067
+TION	-6.94666
+▁NOM	-6.94742
+▁MAR	-6.94757
+AS	-6.95132
+MAN	-6.95299
+LÉ	-6.9536
+ILL	-6.95456
+▁COM	-6.96091
+▁PA	-6.96811
+W	-6.97204
+TURE	-6.97208
+MIN	-6.98243
+▁MAIS	-6.9843
+VE	-6.98613
+ITE	-6.98699
+IX	-6.98924
+ANCE	-6.99379
+ENCE	-6.99452
+OP	-7.00439
+EMP	-7.01487
+ALL	-7.01562
+EUX	-7.0194
+▁K	-7.02409
+▁ÉTAIT	-7.02541
+▁FAIT	-7.03542
+J	-7.03897
+▁TOUT	-7.04055
+TIQUE	-7.04819
+PE	-7.0542
+UV	-7.06736
+▁PLA	-7.06843
+IRE	-7.07173
+ENS	-7.07267
+▁Y	-7.08027
+IG	-7.08324
+VO	-7.08886
+VEN	-7.08955
+ABLE	-7.09118
+▁AUX	-7.09488
+▁MON	-7.10007
+ÊT	-7.10148
+▁AUSSI	-7.10337
+▁FOR	-7.1046
+TRA	-7.10535
+LES	-7.10662
+NI	-7.11363
+TRI	-7.1155
+▁DIS	-7.12849
+▁MI	-7.13277
+▁TRA	-7.13732
+▁CENT	-7.14084
+▁TO	-7.14595
+ÉS	-7.14696
+TTE	-7.14853
+EX	-7.15105
+▁APP	-7.15361
+▁GRAND	-7.1556
+▁AR	-7.15993
+INS	-7.16085
+▁NO	-7.16217
+▁DÉC	-7.16942
+MO	-7.17708
+▁BR	-7.17793
+▁AN	-7.17923
+ÉES	-7.18741
+ONNE	-7.18794
+▁PRÉ	-7.19409
+▁ME	-7.20081
+▁LUI	-7.20722
+▁FA	-7.21393
+TEN	-7.22018
+AUT	-7.22063
+BL	-7.22212
+IVE	-7.22299
+Ç	-7.22345
+Â	-7.23831
+▁FUT	-7.24785
+▁SO	-7.25014
+▁TROIS	-7.25306
+EAU	-7.25746
+▁ALORS	-7.25977
+TEUR	-7.26764
+▁MÉ	-7.27978
+DA	-7.28468
+▁J	-7.3032
+▁ON	-7.30519
+▁JA	-7.30584
+GUE	-7.31225
+▁LEUR	-7.31485
+ÈME	-7.33414
+▁ONT	-7.33777
+▁W	-7.33813
+▁MÊME	-7.35801
+ACC	-7.36611
+IEN	-7.36761
+▁SAINT	-7.37041
+AINE	-7.3713
+À	-7.37841
+▁VA	-7.38049
+▁FIN	-7.38075
+ICI	-7.38685
+ITION	-7.39214
+▁CES	-7.39695
+▁COUR	-7.40965
+UM	-7.41412
+BRE	-7.42144
+▁PEU	-7.42661
+Î	-7.43206
+TRO	-7.44221
+IENNE	-7.4553
+IDE	-7.46487
+▁REP	-7.46845
+▁JU	-7.48234
+▁VILLE	-7.48283
+▁APRÈS	-7.4882
+▁ÊTRE	-7.50185
+▁RI	-7.50735
+▁VOUS	-7.50844
+▁PLUSIEURS	-7.50953
+▁NA	-7.51404
+▁TH	-7.52054
+ANTE	-7.52681
+TRÈS	-7.55566
+▁SITUÉ	-7.55585
+▁TOUR	-7.57672
+▁PARTIE	-7.58074
+▁FRANC	-7.58851
+▁QUATRE	-7.60502
+▁PER	-7.60579
+VIENT	-7.60672
+▁ENTRE	-7.60832
+ING	-7.61424
+▁PREMIER	-7.61747
+▁CAR	-7.61875
+LON	-7.62346
+FORM	-7.62502
+BA	-7.62598
+VÉ	-7.62913
+IFI	-7.63386
+AIENT	-7.63434
+HI	-7.63915
+▁JO	-7.64691
+TIF	-7.64803
+TANT	-7.64813
+▁PEUT	-7.6495
+STRU	-7.65091
+▁PARTI	-7.6818
+▁COMMUNE	-7.69343
+Ê	-7.70573
+▁REN	-7.71927
+ATEUR	-7.72429
+▁BIEN	-7.72773
+▁PRI	-7.72972
+▁RUE	-7.73029
+▁MONT	-7.73878
+▁PI	-7.74146
+▁JOUR	-7.75127
+AUTRES	-7.75678
+IBLE	-7.76348
+APP	-7.76413
+▁CINQ	-7.77455
+▁PREMIÈRE	-7.7773
+▁MARI	-7.78024
+CK	-7.78135
+▁TROUVE	-7.81049
+ISSE	-7.82038
+▁DONC	-7.82363
+▁GROUPE	-7.84207
+▁JOUE	-7.84684
+▁VERS	-7.84731
+JO	-7.84878
+ÎT	-7.85732
+ÉTAT	-7.86426
+▁FRANÇAIS	-7.86688
+▁LORS	-7.90172
+▁ENSUITE	-7.90256
+▁PUIS	-7.90451
+▁PETIT	-7.90487
+EUSE	-7.90881
+▁AINSI	-7.91868
+▁TRAVAIL	-7.92917
+▁NOUS	-7.93438
+▁QUELQUE	-7.93802
+▁COLL	-7.94043
+▁CERTAIN	-7.94047
+▁LIEU	-7.94101
+▁PRÉSENT	-7.94744
+ÉQUIPE	-7.95119
+▁VINGT	-7.96329
+▁PÈRE	-7.96773
+▁FAMILLE	-7.96931
+▁RU	-7.97689
+▁RENCONTRE	-7.98339
+▁ESPÈCE	-7.98434
+▁FILS	-7.99492
+▁GÉNÉRAL	-7.99556
+▁OB	-7.99882
+▁ÉV	-8.00993
+Ï	-8.03049
+▁PAYS	-8.03417
+▁ANNÉE	-8.03678
+ÉGLISE	-8.04578
+▁PRINCIPAL	-8.05694
+▁GUERRE	-8.06876
+▁SANS	-8.07727
+ANCIEN	-8.09295
+▁CEPENDANT	-8.11907
+▁RESTE	-8.13532
+Œ	-8.14688
+▁PENDANT	-8.15932
+▁TEMPS	-8.17676
+▁FOND	-8.18238
+HUI	-8.18803
+▁RÉGION	-8.19186
+MM	-8.19787
+▁MEMBRE	-8.20795
+Û	-8.20852
+▁TRANS	-8.22004
+▁CLUB	-8.2233
+BERT	-8.23451
+▁DEPUIS	-8.24704
+▁IMP	-8.24718
+PRÈS	-8.24744
+▁SEPT	-8.25346
+▁NATIONAL	-8.27048
+▁CONNU	-8.27896
+▁VILLAGE	-8.28281
+▁MORT	-8.28495
+▁ENCORE	-8.2883
+ORGANIS	-8.29212
+HISTOIRE	-8.29341
+Ù	-8.30578
+▁SECOND	-8.31309
+▁NOUVELLE	-8.32129
+ŒUVRE	-8.32595
+ORIGINE	-8.33151
+UNIVERSITÉ	-8.334
+▁UTILISÉ	-8.33568
+▁AUJOURD	-8.33703
+▁COMMUN	-8.34805
+▁FILM	-8.35268
+▁FRÈRE	-8.35616
+▁TITRE	-8.35992
+▁DIRECT	-8.37008
+ÉLECT	-8.38125
+▁FEMME	-8.39511
+▁HUIT	-8.39969
+ÉTAIENT	-8.40294
+ÉCOLE	-8.40896
+▁DERNIER	-8.41137
+▁MONSIEUR	-8.41865
+▁IMPORTANT	-8.41901
+▁PERMET	-8.42395
+▁JUSQU	-8.43115
+▁DROIT	-8.43711
+▁CARRIÈRE	-8.43793
+ARCHI	-8.44301
+▁NOMBREUX	-8.44313
+▁SAISON	-8.44828
+▁NOTAMMENT	-8.4518
+▁PIERRE	-8.46428
+BOURG	-8.46772
+▁DIFFÉRENT	-8.46861
+▁NOUVEAU	-8.48184
+▁TOUJOURS	-8.48767
+▁SIÈGE	-8.50391
+ÉDIT	-8.51508
+▁PERSONNE	-8.51771
+▁SUIVANT	-8.51936
+▁CELUI	-8.52301
+Ë	-9.3779
+Ü	-9.47316
+Q	-9.58463
+Æ	-11.4978

data/lm/3gram.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be4fda53d5a4b94d700114f5a5505173da3539d20931957e5c5be4ad8133a7f
+size 152616228

data/lm/4gram.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fddfa46e7ebac2fa1a1ce3f8ec484a1f0732fda0dda36fb08afb38ae1c89206
+size 314528045

data/lm/G_3_gram.fst.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20bc2acc13d5f994d45c043efca5912e2de4c35c8f02b4e4f9fec3b40fd7394
+size 201842208

data/lm/G_3_gram.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d020d44e201b49b73d86fab4de2e27239b65aa6964af798ff6084c663c8c0f7
+size 125652395

data/lm/G_4_gram.fst.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bacb19ab623009603f2880cf406b2bc58e12e0e3fc199bb22dca06f2cc3dfc3
+size 424054640

decoding_results/fast_beam_search/log-decode-epoch-29-avg-9-streaming-chunk-size-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model-2023-04-03-17-31-21

@@ -0,0 +1,82 @@
+2023-04-03 17:31:21,345 INFO [decode.py:659] Decoding started
+2023-04-03 17:31:21,345 INFO [decode.py:665] Device: cuda:0
+2023-04-03 17:31:21,347 INFO [decode.py:675] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.23.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '62e404dd3f3a811d73e424199b3408e309c06e1a', 'k2-git-date': 'Mon Jan 30 02:26:16 2023', 'lhotse-version': '1.12.0.dev+git.3ccfeb7.clean', 'torch-version': '1.13.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.7', 'python-version': '3.8', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'd74822d-dirty', 'icefall-git-date': 'Tue Mar 21 21:35:32 2023', 'icefall-path': '/home/lishaojie/icefall', 'k2-path': '/home/lishaojie/.conda/envs/env_lishaojie/lib/python3.8/site-packages/k2/__init__.py', 'lhotse-path': '/home/lishaojie/.conda/envs/env_lishaojie/lib/python3.8/site-packages/lhotse/__init__.py', 'hostname': 'cnc533', 'IP address': '127.0.1.1'}, 'epoch': 29, 'iter': 0, 'avg': 9, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7_streaming/exp1'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'fast_beam_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,4,3,2,4', 'feedforward_dims': '1024,1024,2048,2048,1024', 'nhead': '8,8,8,8,8', 'encoder_dims': '384,384,384,384,384', 'attention_dims': '192,192,192,192,192', 'encoder_unmasked_dims': '256,256,256,256,256', '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': 64, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 200, '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_stateless7_streaming/exp1/fast_beam_search'), 'suffix': 'epoch-29-avg-9-streaming-chunk-size-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-04-03 17:31:21,347 INFO [decode.py:677] About to create model
+2023-04-03 17:31:21,749 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.
+2023-04-03 17:31:21,757 INFO [decode.py:748] Calculating the averaged model over epoch range from 20 (excluded) to 29
+2023-04-03 17:31:23,870 INFO [decode.py:782] Number of model parameters: 70369391
+2023-04-03 17:31:23,871 INFO [commonvoice_fr.py:406] About to get test cuts
+2023-04-03 17:31:26,743 INFO [decode.py:560] batch 0/?, cuts processed until now is 27
+2023-04-03 17:31:31,854 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.8338, 1.6836, 1.5364, 1.7643, 2.1272, 2.0399, 1.7407, 1.5925],
+       device='cuda:0'), covar=tensor([0.0367, 0.0349, 0.0585, 0.0342, 0.0213, 0.0459, 0.0350, 0.0414],
+       device='cuda:0'), in_proj_covar=tensor([0.0097, 0.0103, 0.0143, 0.0108, 0.0097, 0.0111, 0.0100, 0.0110],
+       device='cuda:0'), out_proj_covar=tensor([7.4944e-05, 7.9098e-05, 1.1173e-04, 8.2734e-05, 7.5248e-05, 8.1783e-05,
+        7.3728e-05, 8.3511e-05], device='cuda:0')
+2023-04-03 17:31:36,035 INFO [decode.py:560] batch 20/?, cuts processed until now is 604
+2023-04-03 17:31:46,332 INFO [decode.py:560] batch 40/?, cuts processed until now is 1209
+2023-04-03 17:31:54,962 INFO [decode.py:560] batch 60/?, cuts processed until now is 1866
+2023-04-03 17:32:04,386 INFO [decode.py:560] batch 80/?, cuts processed until now is 2422
+2023-04-03 17:32:13,074 INFO [decode.py:560] batch 100/?, cuts processed until now is 3088
+2023-04-03 17:32:14,054 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.2042, 1.9050, 2.4510, 1.6668, 2.2104, 2.4274, 1.7766, 2.5439],
+       device='cuda:0'), covar=tensor([0.1183, 0.2019, 0.1326, 0.1735, 0.0824, 0.1156, 0.2855, 0.0688],
+       device='cuda:0'), in_proj_covar=tensor([0.0188, 0.0202, 0.0188, 0.0186, 0.0170, 0.0210, 0.0213, 0.0194],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:32:22,296 INFO [decode.py:560] batch 120/?, cuts processed until now is 3672
+2023-04-03 17:32:28,822 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.4821, 2.5480, 2.1061, 1.0486, 2.2957, 1.9745, 1.9215, 2.3727],
+       device='cuda:0'), covar=tensor([0.0910, 0.0618, 0.1588, 0.1982, 0.1334, 0.2716, 0.2164, 0.0818],
+       device='cuda:0'), in_proj_covar=tensor([0.0167, 0.0187, 0.0196, 0.0178, 0.0206, 0.0207, 0.0220, 0.0192],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:32:30,833 INFO [decode.py:560] batch 140/?, cuts processed until now is 4348
+2023-04-03 17:32:39,389 INFO [decode.py:560] batch 160/?, cuts processed until now is 5035
+2023-04-03 17:32:41,458 INFO [zipformer.py:2441] attn_weights_entropy = tensor([0.5151, 1.7409, 1.7151, 0.9089, 1.8593, 1.9981, 2.0410, 1.5445],
+       device='cuda:0'), covar=tensor([0.0868, 0.0573, 0.0496, 0.0555, 0.0400, 0.0600, 0.0273, 0.0678],
+       device='cuda:0'), in_proj_covar=tensor([0.0119, 0.0146, 0.0125, 0.0119, 0.0128, 0.0127, 0.0138, 0.0146],
+       device='cuda:0'), out_proj_covar=tensor([8.7160e-05, 1.0465e-04, 8.8840e-05, 8.3773e-05, 8.9721e-05, 9.0117e-05,
+        9.8475e-05, 1.0448e-04], device='cuda:0')
+2023-04-03 17:32:48,122 INFO [decode.py:560] batch 180/?, cuts processed until now is 5674
+2023-04-03 17:32:56,943 INFO [decode.py:560] batch 200/?, cuts processed until now is 6301
+2023-04-03 17:33:05,928 INFO [decode.py:560] batch 220/?, cuts processed until now is 6914
+2023-04-03 17:33:14,496 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.3674, 2.1843, 2.3572, 1.7864, 2.2139, 2.4677, 2.4855, 1.9260],
+       device='cuda:0'), covar=tensor([0.0445, 0.0549, 0.0557, 0.0678, 0.1166, 0.0458, 0.0437, 0.0916],
+       device='cuda:0'), in_proj_covar=tensor([0.0128, 0.0133, 0.0136, 0.0116, 0.0123, 0.0135, 0.0136, 0.0158],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0001, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:33:14,778 INFO [decode.py:560] batch 240/?, cuts processed until now is 7540
+2023-04-03 17:33:23,635 INFO [decode.py:560] batch 260/?, cuts processed until now is 8161
+2023-04-03 17:33:27,250 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.4658, 2.5376, 2.1602, 1.2614, 2.3429, 2.0655, 1.9856, 2.4390],
+       device='cuda:0'), covar=tensor([0.0989, 0.0582, 0.1814, 0.1883, 0.1155, 0.2226, 0.2119, 0.0799],
+       device='cuda:0'), in_proj_covar=tensor([0.0167, 0.0187, 0.0196, 0.0178, 0.0206, 0.0207, 0.0220, 0.0192],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:33:32,012 INFO [decode.py:560] batch 280/?, cuts processed until now is 8857
+2023-04-03 17:33:39,857 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.5870, 2.6057, 2.1060, 1.0188, 2.3087, 2.0434, 1.9922, 2.3943],
+       device='cuda:0'), covar=tensor([0.0943, 0.0679, 0.1608, 0.1959, 0.1304, 0.2489, 0.2117, 0.0787],
+       device='cuda:0'), in_proj_covar=tensor([0.0167, 0.0187, 0.0196, 0.0178, 0.0206, 0.0207, 0.0220, 0.0192],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:33:40,207 INFO [decode.py:560] batch 300/?, cuts processed until now is 9574
+2023-04-03 17:33:49,272 INFO [decode.py:560] batch 320/?, cuts processed until now is 10169
+2023-04-03 17:33:57,944 INFO [decode.py:560] batch 340/?, cuts processed until now is 10810
+2023-04-03 17:34:06,479 INFO [decode.py:560] batch 360/?, cuts processed until now is 11452
+2023-04-03 17:34:14,029 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.5451, 2.5973, 2.1309, 1.0323, 2.3093, 2.0920, 1.9761, 2.4208],
+       device='cuda:0'), covar=tensor([0.0829, 0.0689, 0.1334, 0.1924, 0.1226, 0.2190, 0.2106, 0.0793],
+       device='cuda:0'), in_proj_covar=tensor([0.0167, 0.0187, 0.0196, 0.0178, 0.0206, 0.0207, 0.0220, 0.0192],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:34:14,816 INFO [decode.py:560] batch 380/?, cuts processed until now is 12133
+2023-04-03 17:34:24,080 INFO [decode.py:560] batch 400/?, cuts processed until now is 12706
+2023-04-03 17:34:33,187 INFO [decode.py:560] batch 420/?, cuts processed until now is 13299
+2023-04-03 17:34:42,380 INFO [decode.py:560] batch 440/?, cuts processed until now is 13891
+2023-04-03 17:34:51,250 INFO [decode.py:560] batch 460/?, cuts processed until now is 14515
+2023-04-03 17:34:59,929 INFO [decode.py:560] batch 480/?, cuts processed until now is 15158
+2023-04-03 17:35:08,659 INFO [decode.py:560] batch 500/?, cuts processed until now is 15743
+2023-04-03 17:35:11,772 INFO [decode.py:576] The transcripts are stored in pruned_transducer_stateless7_streaming/exp1/fast_beam_search/recogs-test-cv-beam_20.0_max_contexts_8_max_states_64-epoch-29-avg-9-streaming-chunk-size-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-04-03 17:35:12,013 INFO [utils.py:558] [test-cv-beam_20.0_max_contexts_8_max_states_64] %WER 10.25% [16082 / 156915, 1180 ins, 1721 del, 13181 sub ]
+2023-04-03 17:35:12,601 INFO [decode.py:589] Wrote detailed error stats to pruned_transducer_stateless7_streaming/exp1/fast_beam_search/errs-test-cv-beam_20.0_max_contexts_8_max_states_64-epoch-29-avg-9-streaming-chunk-size-64-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
+2023-04-03 17:35:12,601 INFO [decode.py:609] 
+For test-cv, WER of different settings are:
+beam_20.0_max_contexts_8_max_states_64	10.25	best for test-cv
+
+2023-04-03 17:35:12,601 INFO [decode.py:808] Done!

decoding_results/fast_beam_search/wer-summary-test-cv-beam_20.0_max_contexts_8_max_states_64.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_20.0_max_contexts_8_max_states_64	10.25

decoding_results/greedy_search/log-decode-epoch-29-avg-9-streaming-chunk-size-64-context-2-max-sym-per-frame-1-use-averaged-model-2023-04-03-17-20-40

@@ -0,0 +1,52 @@
+2023-04-03 17:20:40,951 INFO [decode.py:659] Decoding started
+2023-04-03 17:20:40,952 INFO [decode.py:665] Device: cuda:0
+2023-04-03 17:20:40,953 INFO [decode.py:675] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.23.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '62e404dd3f3a811d73e424199b3408e309c06e1a', 'k2-git-date': 'Mon Jan 30 02:26:16 2023', 'lhotse-version': '1.12.0.dev+git.3ccfeb7.clean', 'torch-version': '1.13.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.7', 'python-version': '3.8', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'd74822d-dirty', 'icefall-git-date': 'Tue Mar 21 21:35:32 2023', 'icefall-path': '/home/lishaojie/icefall', 'k2-path': '/home/lishaojie/.conda/envs/env_lishaojie/lib/python3.8/site-packages/k2/__init__.py', 'lhotse-path': '/home/lishaojie/.conda/envs/env_lishaojie/lib/python3.8/site-packages/lhotse/__init__.py', 'hostname': 'cnc533', 'IP address': '127.0.1.1'}, 'epoch': 29, 'iter': 0, 'avg': 9, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7_streaming/exp1'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'greedy_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,4,3,2,4', 'feedforward_dims': '1024,1024,2048,2048,1024', 'nhead': '8,8,8,8,8', 'encoder_dims': '384,384,384,384,384', 'attention_dims': '192,192,192,192,192', 'encoder_unmasked_dims': '256,256,256,256,256', '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': 64, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 200, '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_stateless7_streaming/exp1/greedy_search'), 'suffix': 'epoch-29-avg-9-streaming-chunk-size-64-context-2-max-sym-per-frame-1-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-04-03 17:20:40,954 INFO [decode.py:677] About to create model
+2023-04-03 17:20:41,325 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.
+2023-04-03 17:20:41,332 INFO [decode.py:748] Calculating the averaged model over epoch range from 20 (excluded) to 29
+2023-04-03 17:20:43,416 INFO [decode.py:782] Number of model parameters: 70369391
+2023-04-03 17:20:43,416 INFO [commonvoice_fr.py:406] About to get test cuts
+2023-04-03 17:20:46,076 INFO [decode.py:560] batch 0/?, cuts processed until now is 27
+2023-04-03 17:20:56,934 INFO [decode.py:560] batch 50/?, cuts processed until now is 1548
+2023-04-03 17:21:07,967 INFO [decode.py:560] batch 100/?, cuts processed until now is 3088
+2023-04-03 17:21:11,846 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.1787, 1.8910, 2.4172, 1.6407, 2.1728, 2.3893, 1.7562, 2.5306],
+       device='cuda:0'), covar=tensor([0.1221, 0.2071, 0.1560, 0.2019, 0.0944, 0.1410, 0.2892, 0.0782],
+       device='cuda:0'), in_proj_covar=tensor([0.0188, 0.0202, 0.0188, 0.0186, 0.0170, 0.0210, 0.0213, 0.0194],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:21:19,943 INFO [decode.py:560] batch 150/?, cuts processed until now is 4693
+2023-04-03 17:21:24,480 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.9368, 4.1410, 3.9511, 2.1512, 4.1722, 3.3482, 1.1814, 3.0681],
+       device='cuda:0'), covar=tensor([0.1757, 0.1534, 0.1609, 0.2749, 0.0958, 0.0773, 0.3330, 0.1192],
+       device='cuda:0'), in_proj_covar=tensor([0.0149, 0.0177, 0.0157, 0.0127, 0.0159, 0.0121, 0.0146, 0.0122],
+       device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0003, 0.0003, 0.0002, 0.0003, 0.0002, 0.0003, 0.0002],
+       device='cuda:0')
+2023-04-03 17:21:30,520 INFO [decode.py:560] batch 200/?, cuts processed until now is 6301
+2023-04-03 17:21:38,318 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.2529, 2.0297, 1.8643, 2.1288, 1.9791, 1.9835, 1.9948, 2.7326],
+       device='cuda:0'), covar=tensor([0.3832, 0.5126, 0.3710, 0.4009, 0.4766, 0.2687, 0.4275, 0.1859],
+       device='cuda:0'), in_proj_covar=tensor([0.0286, 0.0261, 0.0233, 0.0273, 0.0255, 0.0225, 0.0254, 0.0234],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:21:41,318 INFO [decode.py:560] batch 250/?, cuts processed until now is 7825
+2023-04-03 17:21:45,845 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.8310, 1.7597, 1.6839, 1.8309, 1.2796, 3.4939, 1.4962, 1.9513],
+       device='cuda:0'), covar=tensor([0.3100, 0.2143, 0.1930, 0.2158, 0.1619, 0.0206, 0.2399, 0.1100],
+       device='cuda:0'), in_proj_covar=tensor([0.0130, 0.0115, 0.0120, 0.0123, 0.0112, 0.0094, 0.0093, 0.0093],
+       device='cuda:0'), out_proj_covar=tensor([0.0006, 0.0005, 0.0005, 0.0006, 0.0005, 0.0004, 0.0005, 0.0004],
+       device='cuda:0')
+2023-04-03 17:21:51,496 INFO [decode.py:560] batch 300/?, cuts processed until now is 9574
+2023-04-03 17:21:53,631 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.9710, 1.4775, 2.1112, 2.0248, 1.8644, 1.8023, 1.9569, 1.9764],
+       device='cuda:0'), covar=tensor([0.4725, 0.4362, 0.3711, 0.4021, 0.5538, 0.4317, 0.5152, 0.3214],
+       device='cuda:0'), in_proj_covar=tensor([0.0260, 0.0243, 0.0263, 0.0289, 0.0289, 0.0265, 0.0295, 0.0247],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:22:02,103 INFO [decode.py:560] batch 350/?, cuts processed until now is 11145
+2023-04-03 17:22:12,758 INFO [decode.py:560] batch 400/?, cuts processed until now is 12706
+2023-04-03 17:22:23,693 INFO [decode.py:560] batch 450/?, cuts processed until now is 14224
+2023-04-03 17:22:34,416 INFO [decode.py:560] batch 500/?, cuts processed until now is 15743
+2023-04-03 17:22:35,701 INFO [decode.py:576] The transcripts are stored in pruned_transducer_stateless7_streaming/exp1/greedy_search/recogs-test-cv-greedy_search-epoch-29-avg-9-streaming-chunk-size-64-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-04-03 17:22:35,945 INFO [utils.py:558] [test-cv-greedy_search] %WER 10.57% [16585 / 156915, 1231 ins, 1791 del, 13563 sub ]
+2023-04-03 17:22:36,536 INFO [decode.py:589] Wrote detailed error stats to pruned_transducer_stateless7_streaming/exp1/greedy_search/errs-test-cv-greedy_search-epoch-29-avg-9-streaming-chunk-size-64-context-2-max-sym-per-frame-1-use-averaged-model.txt
+2023-04-03 17:22:36,536 INFO [decode.py:609] 
+For test-cv, WER of different settings are:
+greedy_search	10.57	best for test-cv
+
+2023-04-03 17:22:36,537 INFO [decode.py:808] Done!

decoding_results/greedy_search/wer-summary-test-cv-greedy_search.txt

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search	10.57

decoding_results/modified_beam_search/log-decode-epoch-29-avg-9-streaming-chunk-size-64-modified_beam_search-beam-size-4-use-averaged-model-2023-04-03-17-22-38

@@ -0,0 +1,82 @@
+2023-04-03 17:22:38,516 INFO [decode.py:659] Decoding started
+2023-04-03 17:22:38,516 INFO [decode.py:665] Device: cuda:0
+2023-04-03 17:22:38,518 INFO [decode.py:675] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.23.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '62e404dd3f3a811d73e424199b3408e309c06e1a', 'k2-git-date': 'Mon Jan 30 02:26:16 2023', 'lhotse-version': '1.12.0.dev+git.3ccfeb7.clean', 'torch-version': '1.13.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.7', 'python-version': '3.8', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'd74822d-dirty', 'icefall-git-date': 'Tue Mar 21 21:35:32 2023', 'icefall-path': '/home/lishaojie/icefall', 'k2-path': '/home/lishaojie/.conda/envs/env_lishaojie/lib/python3.8/site-packages/k2/__init__.py', 'lhotse-path': '/home/lishaojie/.conda/envs/env_lishaojie/lib/python3.8/site-packages/lhotse/__init__.py', 'hostname': 'cnc533', 'IP address': '127.0.1.1'}, 'epoch': 29, 'iter': 0, 'avg': 9, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7_streaming/exp1'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'modified_beam_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,4,3,2,4', 'feedforward_dims': '1024,1024,2048,2048,1024', 'nhead': '8,8,8,8,8', 'encoder_dims': '384,384,384,384,384', 'attention_dims': '192,192,192,192,192', 'encoder_unmasked_dims': '256,256,256,256,256', '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': 64, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 200, '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_stateless7_streaming/exp1/modified_beam_search'), 'suffix': 'epoch-29-avg-9-streaming-chunk-size-64-modified_beam_search-beam-size-4-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2023-04-03 17:22:38,519 INFO [decode.py:677] About to create model
+2023-04-03 17:22:38,918 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.
+2023-04-03 17:22:38,925 INFO [decode.py:748] Calculating the averaged model over epoch range from 20 (excluded) to 29
+2023-04-03 17:22:40,997 INFO [decode.py:782] Number of model parameters: 70369391
+2023-04-03 17:22:40,997 INFO [commonvoice_fr.py:406] About to get test cuts
+2023-04-03 17:22:44,389 INFO [decode.py:560] batch 0/?, cuts processed until now is 27
+2023-04-03 17:23:03,653 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.4396, 2.2447, 2.4559, 1.5968, 2.3244, 2.4744, 2.4945, 1.9745],
+       device='cuda:0'), covar=tensor([0.0486, 0.0604, 0.0566, 0.0803, 0.0805, 0.0564, 0.0533, 0.1100],
+       device='cuda:0'), in_proj_covar=tensor([0.0128, 0.0133, 0.0136, 0.0116, 0.0123, 0.0135, 0.0136, 0.0158],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0001, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:23:05,745 INFO [decode.py:560] batch 20/?, cuts processed until now is 604
+2023-04-03 17:23:23,592 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.0329, 1.8940, 1.7735, 2.1519, 2.5543, 2.1581, 1.8200, 1.6895],
+       device='cuda:0'), covar=tensor([0.2199, 0.2101, 0.1994, 0.1657, 0.1436, 0.1120, 0.2161, 0.2030],
+       device='cuda:0'), in_proj_covar=tensor([0.0242, 0.0208, 0.0212, 0.0195, 0.0242, 0.0187, 0.0214, 0.0202],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:23:26,475 INFO [decode.py:560] batch 40/?, cuts processed until now is 1209
+2023-04-03 17:23:41,645 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.7772, 2.7137, 2.1413, 1.0557, 2.3674, 2.2655, 2.0341, 2.4959],
+       device='cuda:0'), covar=tensor([0.0948, 0.0634, 0.1572, 0.1977, 0.1178, 0.2220, 0.2033, 0.0825],
+       device='cuda:0'), in_proj_covar=tensor([0.0167, 0.0187, 0.0196, 0.0178, 0.0206, 0.0207, 0.0220, 0.0192],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:23:46,667 INFO [decode.py:560] batch 60/?, cuts processed until now is 1866
+2023-04-03 17:24:07,713 INFO [decode.py:560] batch 80/?, cuts processed until now is 2422
+2023-04-03 17:24:10,930 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.5944, 1.6332, 1.4009, 1.6980, 2.0331, 1.9103, 1.6203, 1.4564],
+       device='cuda:0'), covar=tensor([0.0370, 0.0328, 0.0636, 0.0290, 0.0200, 0.0398, 0.0360, 0.0438],
+       device='cuda:0'), in_proj_covar=tensor([0.0097, 0.0103, 0.0143, 0.0108, 0.0097, 0.0111, 0.0100, 0.0110],
+       device='cuda:0'), out_proj_covar=tensor([7.4944e-05, 7.9098e-05, 1.1173e-04, 8.2734e-05, 7.5248e-05, 8.1783e-05,
+        7.3728e-05, 8.3511e-05], device='cuda:0')
+2023-04-03 17:24:19,887 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.5455, 2.5531, 2.0976, 0.9939, 2.3244, 2.0391, 1.9380, 2.4056],
+       device='cuda:0'), covar=tensor([0.0949, 0.0639, 0.1516, 0.2032, 0.1282, 0.2361, 0.2408, 0.0816],
+       device='cuda:0'), in_proj_covar=tensor([0.0167, 0.0187, 0.0196, 0.0178, 0.0206, 0.0207, 0.0220, 0.0192],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:24:27,881 INFO [decode.py:560] batch 100/?, cuts processed until now is 3088
+2023-04-03 17:24:48,430 INFO [decode.py:560] batch 120/?, cuts processed until now is 3672
+2023-04-03 17:25:08,496 INFO [decode.py:560] batch 140/?, cuts processed until now is 4348
+2023-04-03 17:25:28,540 INFO [decode.py:560] batch 160/?, cuts processed until now is 5035
+2023-04-03 17:25:40,611 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.4775, 2.3269, 2.5159, 1.6390, 2.4735, 2.5963, 2.5525, 2.0379],
+       device='cuda:0'), covar=tensor([0.0466, 0.0579, 0.0534, 0.0716, 0.0834, 0.0513, 0.0447, 0.1035],
+       device='cuda:0'), in_proj_covar=tensor([0.0128, 0.0133, 0.0136, 0.0116, 0.0123, 0.0135, 0.0136, 0.0158],
+       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0001, 0.0002, 0.0002, 0.0002, 0.0002],
+       device='cuda:0')
+2023-04-03 17:25:48,922 INFO [decode.py:560] batch 180/?, cuts processed until now is 5674
+2023-04-03 17:26:09,282 INFO [decode.py:560] batch 200/?, cuts processed until now is 6301
+2023-04-03 17:26:29,657 INFO [decode.py:560] batch 220/?, cuts processed until now is 6914
+2023-04-03 17:26:50,151 INFO [decode.py:560] batch 240/?, cuts processed until now is 7540
+2023-04-03 17:27:10,601 INFO [decode.py:560] batch 260/?, cuts processed until now is 8161
+2023-04-03 17:27:30,848 INFO [decode.py:560] batch 280/?, cuts processed until now is 8857
+2023-04-03 17:27:50,769 INFO [decode.py:560] batch 300/?, cuts processed until now is 9574
+2023-04-03 17:28:11,398 INFO [decode.py:560] batch 320/?, cuts processed until now is 10169
+2023-04-03 17:28:25,548 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.8605, 1.7340, 2.4232, 3.4970, 2.3920, 2.5277, 1.1464, 2.9314],
+       device='cuda:0'), covar=tensor([0.1522, 0.1223, 0.1074, 0.0445, 0.0713, 0.1245, 0.1648, 0.0431],
+       device='cuda:0'), in_proj_covar=tensor([0.0097, 0.0114, 0.0131, 0.0162, 0.0098, 0.0133, 0.0122, 0.0098],
+       device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0003, 0.0004, 0.0004, 0.0003, 0.0004, 0.0003, 0.0003],
+       device='cuda:0')
+2023-04-03 17:28:31,696 INFO [decode.py:560] batch 340/?, cuts processed until now is 10810
+2023-04-03 17:28:52,180 INFO [decode.py:560] batch 360/?, cuts processed until now is 11452
+2023-04-03 17:29:12,247 INFO [decode.py:560] batch 380/?, cuts processed until now is 12133
+2023-04-03 17:29:33,066 INFO [decode.py:560] batch 400/?, cuts processed until now is 12706
+2023-04-03 17:29:53,675 INFO [decode.py:560] batch 420/?, cuts processed until now is 13299
+2023-04-03 17:30:07,997 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.8529, 1.7486, 1.5706, 1.8211, 2.1766, 2.0610, 1.7289, 1.5829],
+       device='cuda:0'), covar=tensor([0.0370, 0.0322, 0.0575, 0.0276, 0.0210, 0.0417, 0.0338, 0.0404],
+       device='cuda:0'), in_proj_covar=tensor([0.0097, 0.0103, 0.0143, 0.0108, 0.0097, 0.0111, 0.0100, 0.0110],
+       device='cuda:0'), out_proj_covar=tensor([7.4944e-05, 7.9098e-05, 1.1173e-04, 8.2734e-05, 7.5248e-05, 8.1783e-05,
+        7.3728e-05, 8.3511e-05], device='cuda:0')
+2023-04-03 17:30:13,957 INFO [decode.py:560] batch 440/?, cuts processed until now is 13891
+2023-04-03 17:30:34,408 INFO [decode.py:560] batch 460/?, cuts processed until now is 14515
+2023-04-03 17:30:54,607 INFO [decode.py:560] batch 480/?, cuts processed until now is 15158
+2023-04-03 17:31:14,650 INFO [decode.py:560] batch 500/?, cuts processed until now is 15743
+2023-04-03 17:31:18,578 INFO [decode.py:576] The transcripts are stored in pruned_transducer_stateless7_streaming/exp1/modified_beam_search/recogs-test-cv-beam_size_4-epoch-29-avg-9-streaming-chunk-size-64-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-04-03 17:31:18,889 INFO [utils.py:558] [test-cv-beam_size_4] %WER 10.19% [15988 / 156915, 1250 ins, 1549 del, 13189 sub ]
+2023-04-03 17:31:19,408 INFO [decode.py:589] Wrote detailed error stats to pruned_transducer_stateless7_streaming/exp1/modified_beam_search/errs-test-cv-beam_size_4-epoch-29-avg-9-streaming-chunk-size-64-modified_beam_search-beam-size-4-use-averaged-model.txt
+2023-04-03 17:31:19,408 INFO [decode.py:609] 
+For test-cv, WER of different settings are:
+beam_size_4	10.19	best for test-cv
+
+2023-04-03 17:31:19,408 INFO [decode.py:808] Done!

decoding_results/modified_beam_search/wer-summary-test-cv-beam_size_4.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_size_4	10.19