init update

README.md

@@ -0,0 +1 @@
+See https://github.com/k2-fsa/icefall/pull/1464

data/lang_bbpe_500/.gitattributes

@@ -0,0 +1,5 @@
+lexicon.txt filter=lfs diff=lfs merge=lfs -text
+lexicon_disambig.txt filter=lfs diff=lfs merge=lfs -text
+tokens.txt filter=lfs diff=lfs merge=lfs -text
+words.txt filter=lfs diff=lfs merge=lfs -text
+text filter=lfs diff=lfs merge=lfs -text

data/lang_bbpe_500/HLG.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8687c95087cde6f19eb1a3da6e991cea6421ee6a29e56703e6e77dd362809c95
+size 314849055

data/lang_bbpe_500/L.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9186950ad99a88c69e30f684fc530c7cf19e326b1f6d66f2b965452fe9d2bfc8
+size 3508519

data/lang_bbpe_500/LG.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b64480bde684f917dc47355d544cf0db8faf381b2094b4d6e2844f7a9632412
+size 84961187

data/lang_bbpe_500/L_disambig.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b115aa88c97b09bec8b6de9588d2d1b28c1032ebeccc611c596315ba054eaf
+size 3579367

data/lang_bbpe_500/Linv.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb66c90e9769439dac4bf6c6f7dc9120160c083f45e4d9d461f41957bf60ad8
+size 3508519

data/lang_bbpe_500/bbpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5964d80e4634fc1d1630c603ba54735e49d7593742879929ab438c57d4114c96
+size 246126

data/lang_bbpe_500/lexicon.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09bd54b1e008c4ed1ed12387e980fe2a7e1d77a8727c8fb911e9f02c984cb858
+size 1292685

data/lang_bbpe_500/lexicon_disambig.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbabfd73b0c8c6f71211c5cec45dc0649a19e0b4901759f0536040d34b5fe611
+size 1303308

data/lang_bbpe_500/text

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd887d311d3295c7a72b6aa046eb3d58f3585741aff768414ceebda0645569e
+size 7684231

data/lang_bbpe_500/tokens.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a3d16785340e55786a3d21ba4da4d155d8033b9d351626c7253c7f560d2558
+size 6331

data/lang_bbpe_500/unigram_500.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5964d80e4634fc1d1630c603ba54735e49d7593742879929ab438c57d4114c96
+size 246126

data/lang_bbpe_500/unigram_500.vocab

@@ -0,0 +1,500 @@
+<blk>	0
+<sos/eos>	0
+<unk>	0
+▁ƌ	-3.19716
+▁ƍ	-3.37846
+▁Ǝ	-3.8666
+▁ƎĽĥ	-3.89993
+▁Ə	-4.09624
+▁Ɛ	-4.35942
+▁ƋŞġ	-4.55055
+ĩ	-4.75878
+Ŕ	-4.80797
+Ī	-4.81606
+Į	-4.94232
+Ş	-5.00197
+Ő	-5.0194
+ł	-5.02456
+ť	-5.05381
+Ģ	-5.05508
+▁ƌŁŎ	-5.07018
+ļ	-5.1054
+ń	-5.14267
+ĺ	-5.15195
+Ť	-5.16014
+ŗ	-5.16186
+Ŗ	-5.18595
+▁ƌİ	-5.2022
+ħ	-5.20415
+š	-5.23155
+Ħ	-5.24698
+ţ	-5.25781
+ŝ	-5.26309
+œ	-5.27034
+ġ	-5.27961
+Ł	-5.2802
+ņ	-5.2807
+▁ƍĻŕ	-5.28214
+ī	-5.28272
+▁ƋŞœ	-5.29616
+Š	-5.3099
+Ś	-5.31238
+▁ƌĮĢ	-5.31462
+▁ƋŠŠ	-5.34844
+Ĵ	-5.36336
+ŕ	-5.36721
+▁ƍŁĪ	-5.40456
+Ň	-5.41222
+ŋ	-5.41951
+Ŋ	-5.42924
+Ō	-5.43171
+▁ƋŠħ	-5.43315
+▁ƋŠĭ	-5.43392
+▁Ǝš	-5.43517
+ř	-5.43851
+▁ƋŞī	-5.44169
+ĵ	-5.45028
+Ļ	-5.46384
+▁ƋŞĮ	-5.46761
+▁ƌľţ	-5.47836
+ĸ	-5.47966
+ľ	-5.48268
+ō	-5.49272
+ŏ	-5.49277
+Ĺ	-5.50156
+▁ƌŞģ	-5.50943
+ň	-5.51563
+Ĥ	-5.51939
+Ĭ	-5.52276
+į	-5.52282
+Ņ	-5.52406
+ĭ	-5.53405
+ķ	-5.5344
+▁ƌŊō	-5.54566
+ģ	-5.55137
+Ř	-5.56234
+▁ƋŞĽ	-5.5747
+Ľ	-5.58446
+Ķ	-5.58867
+▁ƋŞŠ	-5.59075
+Ţ	-5.5949
+İ	-5.60126
+▁ƌşŚ	-5.61297
+ş	-5.61799
+▁ƋŞĪ	-5.70592
+ĥ	-5.71751
+Ŏ	-5.72581
+▁ƌİĴ	-5.734
+▁Ƌţ	-5.73857
+▁ƌĦ	-5.73882
+Ĩ	-5.74167
+▁Ƌš	-5.8087
+▁ƋŞŐ	-5.81474
+Œ	-5.81861
+▁ƌĨŠ	-5.8218
+▁ƌŁŖ	-5.8229
+▁Əņĭ	-5.83288
+▁ƌĦŒ	-5.83919
+▁ƌĩħ	-5.83953
+▁ƋŢĽ	-5.84644
+▁ƏŚ	-5.84917
+ı	-5.86467
+▁ƍĩı	-5.88557
+▁ƌĵĭ	-5.90836
+▁Əťļ	-5.90872
+ő	-5.92808
+Ŝ	-5.94431
+▁ƌĩŖ	-5.95008
+▁ƋŠō	-5.95681
+Ń	-5.96487
+▁ƌŕş	-5.96726
+▁ƋŠķ	-5.98296
+▁ƋŠ	-5.98395
+▁ƍĺŜ	-5.98461
+▁ƌŁŠ	-5.9885
+▁ƏĤţ	-5.99015
+▁ƍĬ	-5.99308
+▁ƍĩť	-5.99998
+▁Ɛġ	-6.012
+▁ƋŞ	-6.0229
+▁ƍłŋ	-6.02655
+▁Əŕ	-6.03123
+▁ƍĹŖ	-6.03545
+▁Ƌšŋ	-6.03769
+▁ƎļŤ	-6.04031
+▁ƍĺŋ	-6.07482
+▁ƋşĬ	-6.10443
+▁Ƌş	-6.1052
+▁ƏġĦ	-6.1086
+▁ƌŖħ	-6.11159
+▁ƏŌĢ	-6.11263
+▁ƎįŖ	-6.11464
+▁ƌŔŜ	-6.13157
+▁ƌľľ	-6.14532
+▁Əśĥ	-6.15595
+▁ƌŊĽ	-6.16649
+▁ƍŁĩ	-6.17773
+▁ƐľŜ	-6.19122
+▁Ƌşń	-6.19929
+▁ƍĹş	-6.20167
+▁ƌıį	-6.20384
+▁ƏĨ	-6.20649
+▁ƍŁŠ	-6.21703
+▁ƋŞĬ	-6.22246
+▁Ǝķń	-6.22305
+▁ƋŠį	-6.2236
+▁ƌĪĮ	-6.22885
+▁ƍŕķ	-6.24515
+▁Ǝģş	-6.25851
+▁ƌŢġ	-6.26487
+▁ƐőĻ	-6.28347
+▁ƌīŎ	-6.29021
+▁Ǝšİ	-6.32286
+▁Əťľ	-6.32585
+▁ƍīŋ	-6.3345
+▁ƎķŎ	-6.34218
+▁Əśľ	-6.35403
+▁ƋţĶ	-6.35925
+▁ƐĨĴ	-6.3644
+ś	-6.38613
+▁Ƌšŝ	-6.39098
+▁ƏţŌ	-6.40247
+▁ƌİŕ	-6.40269
+▁ƏŇő	-6.40776
+▁ƏťĨ	-6.40784
+▁ƋŞĨ	-6.41243
+▁ƌœı	-6.42182
+▁ƍŁŒ	-6.43345
+▁ƍĪĬ	-6.4338
+▁ƌĦŎ	-6.43499
+▁ƌİŞ	-6.43801
+▁ƋţŁ	-6.44903
+▁ƍŁġ	-6.46051
+▁Ǝķś	-6.46421
+▁ƎľŔ	-6.467
+▁ƌĦő	-6.47982
+▁ƐĤŎ	-6.48043
+▁ƌĦœ	-6.49274
+▁ƌı	-6.4971
+▁ƍĩĴ	-6.50821
+▁ƌīľ	-6.53467
+▁ƌīŅ	-6.53724
+▁ƐłŇ	-6.53788
+▁ƋŞĤ	-6.54633
+▁ƌŠŌ	-6.55184
+▁ƋŢĢ	-6.5633
+▁ƋŠŊ	-6.56532
+▁ƌŔŃ	-6.56756
+▁ƌńį	-6.57743
+▁ƌĦĤ	-6.58198
+▁Ƌşł	-6.58499
+▁ƌŝŘ	-6.5855
+▁ƌŔĽ	-6.58607
+▁ƌŖİ	-6.59051
+▁ƏťĻ	-6.59824
+▁ƌĦŜ	-6.60151
+▁ƌĶĢ	-6.60241
+▁ƌŝŋ	-6.60314
+▁ƌıĭ	-6.60475
+▁Əġĭ	-6.60701
+▁ƎţĴ	-6.60816
+▁ƌıĩ	-6.61271
+▁ƌħĦ	-6.61425
+▁ƌĦř	-6.61917
+▁ƋšĹ	-6.6213
+▁ƋŞį	-6.623
+▁ƍřĸ	-6.62593
+▁ƌŤĺ	-6.62751
+▁ƎŒ	-6.64811
+▁ƌŖŗ	-6.65321
+▁ƏŔŖ	-6.65678
+▁Ǝıħ	-6.66421
+▁ƌĦŋ	-6.66644
+▁Ɛĸť	-6.67939
+▁ƋŠĬ	-6.68516
+▁ƌıĮ	-6.68798
+▁Əś	-6.68867
+▁ƌĸħ	-6.69805
+▁ƌŋř	-6.70211
+▁ƋšŒ	-6.70494
+▁ƐĤţ	-6.70841
+▁ƋŠŒ	-6.70994
+▁ƋŞŊ	-6.7116
+▁ƌşŜ	-6.72638
+▁ƌĩŜ	-6.72911
+▁ƌĭĹ	-6.74188
+▁ƍķť	-6.7514
+▁ƌşř	-6.75474
+▁ƍŁń	-6.76244
+▁ƏņŎ	-6.76775
+▁ƐĨĮ	-6.76956
+▁ƍŒņ	-6.77274
+▁ƋŞš	-6.77455
+▁ƍĮŔ	-6.78155
+▁ƌīņ	-6.78194
+▁Ƌťł	-6.78255
+▁ƌĩŏ	-6.78866
+▁ƐġĽ	-6.79022
+▁ƎľŞ	-6.794
+▁ƐĢĶ	-6.79959
+▁ƋŤ	-6.80011
+▁ƌŊŏ	-6.80894
+▁ƌŗĸ	-6.8179
+▁ƍİı	-6.82488
+▁ƍīĸ	-6.82617
+▁ƌĭĺ	-6.82762
+▁ƐĨİ	-6.82849
+▁ƐĺŚ	-6.83218
+▁ƌĴĻ	-6.83769
+▁ƌšŠ	-6.84596
+▁ƌľŅ	-6.8485
+▁ƍśŝ	-6.85106
+▁ƌŋţ	-6.85296
+▁ƍĪġ	-6.85796
+▁ƍĸŖ	-6.86622
+▁ƎŔņ	-6.87755
+▁ƌŊĹ	-6.87808
+▁ƎŊŠ	-6.88415
+▁ƌĭŠ	-6.88751
+▁ƍľŚ	-6.89993
+▁ƍġō	-6.9102
+▁ƎœĪ	-6.91311
+▁ƌŠķ	-6.92274
+▁Ƌšį	-6.92685
+▁ƌŇŃ	-6.92975
+▁Əťı	-6.93133
+▁ƏŔņ	-6.93208
+▁ƌţĶ	-6.93571
+▁Ɛņş	-6.93584
+▁ƍķŜ	-6.93772
+▁Ƌťņ	-6.94787
+▁ƍĻį	-6.96518
+▁ƐĻ	-6.97996
+▁Ǝłġ	-6.98773
+▁ƏŔŤ	-6.99153
+▁ƍŖĴ	-6.99352
+▁ƏŖĤ	-7.00159
+▁Əōĥ	-7.00256
+▁ƍĭĢ	-7.00855
+▁ƋţĮ	-7.00883
+▁Əśŝ	-7.01024
+▁ƌœŌ	-7.01508
+▁ƌŤĩ	-7.04497
+▁ƍŅŢ	-7.04525
+▁ƍŘņ	-7.04543
+▁Ƌšī	-7.04903
+▁ƍœň	-7.05139
+▁Əģņ	-7.05215
+▁ƌťĤ	-7.05258
+▁ƌİŖ	-7.05538
+▁ƎĥŜ	-7.0732
+▁ƌįš	-7.08255
+▁ƏŤ	-7.08788
+▁ƌŔĪ	-7.08923
+▁ƍœŊ	-7.0894
+▁ƎŤį	-7.09152
+▁ƍŃŁ	-7.0981
+▁ƍĺŅ	-7.1161
+▁ƏĬ	-7.11958
+▁ƐĻń	-7.12495
+▁ƎōĴ	-7.12752
+▁ƎŠť	-7.1287
+▁ƌŌģ	-7.1296
+▁ƌńŠ	-7.13019
+▁ƏŠő	-7.13372
+▁ƐŁġ	-7.14207
+▁ƍĤĦ	-7.14907
+▁ƍŜĩ	-7.15571
+▁ƏťĴ	-7.15889
+▁ƏŚş	-7.16064
+▁ƏŤŤ	-7.1667
+▁ƌİĺ	-7.16705
+▁ƌŞĤ	-7.16808
+▁ƋŞĹ	-7.16887
+▁ƍŅĨ	-7.17123
+▁ƍŁŐ	-7.17708
+▁ƋŞŁ	-7.17868
+▁ƍŗģ	-7.17928
+▁ƍĢŕ	-7.18683
+▁ƋŠľ	-7.18718
+▁ƍœŋ	-7.18878
+▁ƏŕĢ	-7.19008
+▁ƎŁĬ	-7.1915
+▁ƐĨĭ	-7.19848
+▁ƌıĴ	-7.20728
+▁Ǝķŝ	-7.21037
+▁ƌĮĤ	-7.21043
+▁ƌľŃ	-7.21177
+▁ƐĺŎ	-7.2143
+▁ƍķş	-7.21651
+▁ƌŢİ	-7.21941
+▁ƏŕŚ	-7.22107
+▁ƍĥİ	-7.2239
+▁ƍįŋ	-7.22463
+▁Ǝŗř	-7.22499
+▁ƍīġ	-7.25222
+▁ƌİī	-7.2523
+▁Ɛķġ	-7.25232
+▁ƎľĴ	-7.25253
+▁ƍġš	-7.25326
+▁ƍŖŚ	-7.25329
+▁ƏĢķ	-7.25352
+▁Ƌţİ	-7.25534
+▁Ǝšœ	-7.25549
+▁ƍĪĶ	-7.25584
+▁ƏŔŕ	-7.25624
+▁ƋŠť	-7.25755
+▁ƍĸŚ	-7.26318
+▁ƏĨř	-7.26433
+▁ƋšŜ	-7.26677
+▁Əįŝ	-7.27447
+▁ƐļŇ	-7.27894
+▁ƌŢŅ	-7.2813
+▁ƌŢŠ	-7.28651
+▁Ǝįŕ	-7.291
+▁ƏġĢ	-7.29374
+▁Əŕŋ	-7.30514
+▁ƌŗġ	-7.31459
+▁ƎĪş	-7.31631
+▁ƐĺŔ	-7.3168
+▁ƏŚœ	-7.32294
+▁ƌķŔ	-7.32513
+▁Ǝķŗ	-7.32595
+▁ƍŋŢ	-7.32973
+▁Əŝŕ	-7.33158
+▁ƌŊĥ	-7.35735
+▁Ǝřš	-7.36312
+▁ƐŇĻ	-7.36762
+▁ƎōŖ	-7.36854
+▁ƍįŎ	-7.37011
+▁ƌţŗ	-7.38065
+▁ƍĩĻ	-7.38067
+▁ƎœĹ	-7.38105
+▁ƏŔŏ	-7.38235
+▁ƌşť	-7.38297
+▁Ǝšń	-7.38342
+▁Ƌşı	-7.38804
+▁ƌħř	-7.39077
+▁ƍŜŎ	-7.393
+▁ƌŖĴ	-7.39481
+▁ƍĻŤ	-7.39553
+▁ƌŝŗ	-7.40121
+▁ƌŞŞ	-7.40335
+▁ƐŌĹ	-7.40411
+▁ƐĶŜ	-7.40563
+▁ƐļĮ	-7.40689
+▁ƌŔĭ	-7.40758
+▁ƍĩŝ	-7.40847
+▁ƌĩľ	-7.4095
+▁ƎōĮ	-7.41323
+▁ƎőĬ	-7.42286
+▁ƍńŋ	-7.42568
+▁ƍņĩ	-7.43364
+▁Əıŋ	-7.43729
+▁ƎŎĬ	-7.44207
+▁ƎıĤ	-7.44671
+▁ƌŊĨ	-7.45022
+▁ƍĻĶ	-7.45135
+▁ƌīť	-7.45209
+▁ƌĨħ	-7.45284
+▁Ƌť	-7.453
+▁ƍŒŤ	-7.45615
+▁ƌıĥ	-7.45805
+▁ƎĪĭ	-7.4581
+▁ƏŔŊ	-7.46154
+▁ƏŝĴ	-7.4708
+▁Ǝōŕ	-7.4726
+▁ƐġŅ	-7.47302
+▁Ƌšň	-7.48171
+▁ƌœĻ	-7.49111
+▁ƍķŤ	-7.49337
+▁ƏŜĦ	-7.49672
+▁Ɛļŏ	-7.49813
+▁ƌŝŃ	-7.49853
+▁ƌįń	-7.49925
+▁ƌĢĽ	-7.50365
+▁ƎŠō	-7.50453
+▁ƌħĮ	-7.50477
+▁ƋŢŅ	-7.505
+▁ƌŔŇ	-7.5077
+▁ƎĪŏ	-7.50877
+▁ƍŅŝ	-7.51128
+▁ƏŤĤ	-7.51459
+▁ƍĹĨ	-7.51962
+▁ƌĮĸ	-7.5223
+▁Ɛňį	-7.52235
+▁Ǝĸĭ	-7.52834
+▁ƏţŒ	-7.53136
+▁ƌĴī	-7.5314
+▁ƋŤľ	-7.53307
+▁Əōň	-7.53589
+▁ƏœŌ	-7.54836
+▁ƌŋş	-7.55543
+▁ƎįĨ	-7.55666
+▁ƌĮį	-7.55769
+▁ƐŇĥ	-7.56045
+▁Ɛľħ	-7.56263
+▁ƍįĵ	-7.56385
+▁ƌĴŎ	-7.56591
+▁ƍĭĨ	-7.57285
+▁ƌŕŢ	-7.57338
+▁ƌĮĨ	-7.57381
+▁ƍŕİ	-7.57849
+▁ƎĪĨ	-7.5926
+▁ƌťő	-7.5929
+▁ƌŊŚ	-7.59533
+▁ƍŁŕ	-7.59652
+▁ƍŁĮ	-7.59806
+▁ƌŃĬ	-7.60054
+▁ƌĩļ	-7.60532
+▁Əōħ	-7.60735
+▁ƎľŚ	-7.60816
+▁ƎŅķ	-7.61627
+▁ƐłŃ	-7.62093
+▁ƍŠı	-7.62144
+▁ƍĹŕ	-7.6232
+▁ƎŠŌ	-7.62703
+▁ƍĹţ	-7.63111
+▁ƌĩő	-7.63792
+▁ƎŊŤ	-7.6435
+▁ƍŚš	-7.64788
+▁ƐŇħ	-7.64809
+▁ƍķŕ	-7.65523
+▁ƌħľ	-7.6566
+▁ƌļŎ	-7.65925
+▁ƍŎņ	-7.66019
+▁ƐĽŤ	-7.66103
+▁ƌĭš	-7.66153
+▁ƍĤř	-7.66756
+▁ƎįĬ	-7.66772
+▁ƌľŇ	-7.66864
+▁ƍŞŞ	-7.67545
+▁ƍŃĥ	-7.68242
+▁ƐŏŒ	-7.68288
+▁ƍĩĹ	-7.68436
+▁ƍļŠ	-7.68474
+▁ƌŢĸ	-7.68914
+▁ƌŞŌ	-7.69112
+▁ƏŃĮ	-7.69745
+▁ƎĦō	-7.70307
+▁ƎĬı	-7.72098
+▁ƌĮĺ	-7.72345
+▁ƌŘĢ	-7.72504
+▁ƌīŃ	-7.72553
+▁ƌŤŔ	-7.72705
+▁ƌĥť	-7.73721
+▁ƌōĬ	-7.74862
+▁Ɛļı	-7.762
+▁ƍįō	-7.7628
+▁ƌňő	-7.76332
+▁ƎņŔ	-7.76353
+▁ƌŋŋ	-7.76416
+▁ƍłĤ	-7.77251
+Ɩ	-8.585
+Ɛ	-8.5851
+Ə	-8.58521
+Ǝ	-8.58531
+Ƌ	-8.5854
+ƍ	-8.5855
+ƌ	-8.5856
+▁	-8.5857

data/lang_bbpe_500/words.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b9be0095c5158dae04888f4947511a5c70071977bdf4214b85fc18879f150d
+size 566278

decoding_results/fast_beam_search/log-decode-epoch-40-avg-10-beam-20.0-max-contexts-8-max-states-64-blank-penalty-0.0-use-averaged-model-2024-01-16-10-04-04

@@ -0,0 +1,64 @@
+2024-01-16 10:04:04,359 INFO [decode.py:673] Decoding started
+2024-01-16 10:04:04,359 INFO [decode.py:679] Device: cuda:0
+2024-01-16 10:04:04,423 INFO [lexicon.py:168] Loading pre-compiled data/lang_bbpe_500/Linv.pt
+2024-01-16 10:04:04,436 INFO [decode.py:691] {'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': '1.24.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '2989b0b1186fa6022932804f5b39fbb2781ebf42', 'k2-git-date': 'Fri Nov 24 11:34:10 2023', 'lhotse-version': '1.19.0.dev+git.d1ae9c05.dirty', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev/aishell-zipformer-bbpe', 'icefall-git-sha1': 'bce81394-clean', 'icefall-git-date': 'Thu Jan 11 09:56:01 2024', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.4.dev20231207+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.19.0.dev0+git.d1ae9c05.dirty-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1207150822-75498b8c5f-55j4z', 'IP address': '10.177.74.211'}, 'epoch': 40, 'iter': 0, 'avg': 10, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan'), 'bpe_model': 'data/lang_bbpe_500/bbpe.model', 'lang_dir': PosixPath('data/lang_bbpe_500'), 'decoding_method': 'fast_beam_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'ilme_scale': 0.2, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'blank_penalty': 0.0, '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, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 200.0, '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, 'res_dir': PosixPath('zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/fast_beam_search'), 'suffix': 'epoch-40-avg-10-beam-20.0-max-contexts-8-max-states-64-blank-penalty-0.0-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2024-01-16 10:04:04,436 INFO [decode.py:693] About to create model
+2024-01-16 10:04:04,956 INFO [decode.py:760] Calculating the averaged model over epoch range from 30 (excluded) to 40
+2024-01-16 10:04:12,532 INFO [decode.py:791] Number of model parameters: 65549011
+2024-01-16 10:04:12,532 INFO [asr_datamodule.py:371] About to get dev cuts
+2024-01-16 10:04:12,549 INFO [asr_datamodule.py:312] About to create dev dataset
+2024-01-16 10:04:13,059 INFO [asr_datamodule.py:329] About to create dev dataloader
+2024-01-16 10:04:13,059 INFO [asr_datamodule.py:376] About to get test cuts
+2024-01-16 10:04:13,061 INFO [asr_datamodule.py:341] About to create test dataset
+2024-01-16 10:04:15,062 INFO [decode.py:564] batch 0/?, cuts processed until now is 35
+2024-01-16 10:04:27,318 INFO [decode.py:564] batch 20/?, cuts processed until now is 785
+2024-01-16 10:04:39,148 INFO [decode.py:564] batch 40/?, cuts processed until now is 1572
+2024-01-16 10:04:50,338 INFO [decode.py:564] batch 60/?, cuts processed until now is 2433
+2024-01-16 10:05:03,143 INFO [decode.py:564] batch 80/?, cuts processed until now is 3154
+2024-01-16 10:05:11,212 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.7125, 2.7740, 2.7712, 2.0904], device='cuda:0')
+2024-01-16 10:05:14,032 INFO [decode.py:564] batch 100/?, cuts processed until now is 4023
+2024-01-16 10:05:26,372 INFO [decode.py:564] batch 120/?, cuts processed until now is 4776
+2024-01-16 10:05:37,471 INFO [decode.py:564] batch 140/?, cuts processed until now is 5662
+2024-01-16 10:05:39,479 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.1403, 1.6074, 1.8219, 3.2897], device='cuda:0')
+2024-01-16 10:05:45,095 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.1947, 1.4890, 1.7581, 3.0378], device='cuda:0')
+2024-01-16 10:05:48,552 INFO [decode.py:564] batch 160/?, cuts processed until now is 6552
+2024-01-16 10:05:59,780 INFO [decode.py:564] batch 180/?, cuts processed until now is 7386
+2024-01-16 10:06:11,198 INFO [decode.py:564] batch 200/?, cuts processed until now is 8204
+2024-01-16 10:06:11,753 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([4.3423, 3.6335, 3.9994, 3.4270], device='cuda:0')
+2024-01-16 10:06:23,159 INFO [decode.py:564] batch 220/?, cuts processed until now is 8999
+2024-01-16 10:06:36,041 INFO [decode.py:564] batch 240/?, cuts processed until now is 9811
+2024-01-16 10:06:47,892 INFO [decode.py:564] batch 260/?, cuts processed until now is 10620
+2024-01-16 10:06:58,301 INFO [decode.py:564] batch 280/?, cuts processed until now is 11537
+2024-01-16 10:07:10,090 INFO [decode.py:564] batch 300/?, cuts processed until now is 12391
+2024-01-16 10:07:21,683 INFO [decode.py:564] batch 320/?, cuts processed until now is 13152
+2024-01-16 10:07:33,975 INFO [decode.py:564] batch 340/?, cuts processed until now is 13879
+2024-01-16 10:07:45,332 INFO [decode.py:580] The transcripts are stored in zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/fast_beam_search/recogs-dev-blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-10-beam-20.0-max-contexts-8-max-states-64-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 10:07:45,825 INFO [utils.py:565] [dev-blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64] %WER 4.17% [8566 / 205341, 197 ins, 500 del, 7869 sub ]
+2024-01-16 10:07:46,507 INFO [decode.py:598] Wrote detailed error stats to zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/fast_beam_search/errs-dev-blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-10-beam-20.0-max-contexts-8-max-states-64-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 10:07:46,527 INFO [decode.py:614] 
+For dev, WER of different settings are:
+blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64	4.17	best for dev
+
+2024-01-16 10:07:48,132 INFO [decode.py:564] batch 0/?, cuts processed until now is 31
+2024-01-16 10:08:04,342 INFO [decode.py:564] batch 20/?, cuts processed until now is 697
+2024-01-16 10:08:17,927 INFO [decode.py:564] batch 40/?, cuts processed until now is 1395
+2024-01-16 10:08:29,163 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.4244, 2.1965, 2.9948, 2.2683, 2.6988, 2.7314, 2.9246, 2.6597],
+       device='cuda:0')
+2024-01-16 10:08:29,706 INFO [decode.py:564] batch 60/?, cuts processed until now is 2169
+2024-01-16 10:08:33,536 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.5973, 3.2926, 2.6284, 2.3168], device='cuda:0')
+2024-01-16 10:08:43,311 INFO [decode.py:564] batch 80/?, cuts processed until now is 2801
+2024-01-16 10:08:55,694 INFO [decode.py:564] batch 100/?, cuts processed until now is 3578
+2024-01-16 10:09:09,070 INFO [decode.py:564] batch 120/?, cuts processed until now is 4249
+2024-01-16 10:09:20,752 INFO [decode.py:564] batch 140/?, cuts processed until now is 5061
+2024-01-16 10:09:27,732 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([5.9109, 5.6864, 5.6041, 5.6176], device='cuda:0')
+2024-01-16 10:09:32,015 INFO [decode.py:564] batch 160/?, cuts processed until now is 5875
+2024-01-16 10:09:44,614 INFO [decode.py:564] batch 180/?, cuts processed until now is 6581
+2024-01-16 10:09:56,882 INFO [decode.py:564] batch 200/?, cuts processed until now is 7122
+2024-01-16 10:09:58,670 INFO [decode.py:580] The transcripts are stored in zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/fast_beam_search/recogs-test-blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-10-beam-20.0-max-contexts-8-max-states-64-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 10:09:58,892 INFO [utils.py:565] [test-blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64] %WER 4.43% [4646 / 104765, 81 ins, 337 del, 4228 sub ]
+2024-01-16 10:09:59,240 INFO [decode.py:598] Wrote detailed error stats to zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/fast_beam_search/errs-test-blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-10-beam-20.0-max-contexts-8-max-states-64-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 10:09:59,243 INFO [decode.py:614] 
+For test, WER of different settings are:
+blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64	4.43	best for test
+
+2024-01-16 10:09:59,250 INFO [decode.py:832] Done!

decoding_results/fast_beam_search/wer-summary-dev-blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-10-beam-20.0-max-contexts-8-max-states-64-blank-penalty-0.0-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64	4.17

decoding_results/fast_beam_search/wer-summary-test-blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-10-beam-20.0-max-contexts-8-max-states-64-blank-penalty-0.0-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+blank_penalty_0.0_beam_20.0_max_contexts_8_max_states_64	4.43

decoding_results/greedy_search/log-decode-epoch-40-avg-10-context-2-max-sym-per-frame-1-blank-penalty-0.0-use-averaged-model-2024-01-16-08-52-11

@@ -0,0 +1,51 @@
+2024-01-16 08:52:11,884 INFO [decode.py:673] Decoding started
+2024-01-16 08:52:11,884 INFO [decode.py:679] Device: cuda:0
+2024-01-16 08:52:11,964 INFO [lexicon.py:168] Loading pre-compiled data/lang_bbpe_500/Linv.pt
+2024-01-16 08:52:11,978 INFO [decode.py:691] {'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': '1.24.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '2989b0b1186fa6022932804f5b39fbb2781ebf42', 'k2-git-date': 'Fri Nov 24 11:34:10 2023', 'lhotse-version': '1.19.0.dev+git.d1ae9c05.dirty', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev/aishell-zipformer-bbpe', 'icefall-git-sha1': 'bce81394-clean', 'icefall-git-date': 'Thu Jan 11 09:56:01 2024', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.4.dev20231207+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.19.0.dev0+git.d1ae9c05.dirty-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-10-0115153933-6959778564-g28xv', 'IP address': '10.177.77.20'}, 'epoch': 40, 'iter': 0, 'avg': 10, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan'), 'bpe_model': 'data/lang_bbpe_500/bbpe.model', 'lang_dir': PosixPath('data/lang_bbpe_500'), 'decoding_method': 'greedy_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'ilme_scale': 0.2, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'blank_penalty': 0.0, '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, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 200.0, '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, 'res_dir': PosixPath('zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/greedy_search'), 'suffix': 'epoch-40-avg-10-context-2-max-sym-per-frame-1-blank-penalty-0.0-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2024-01-16 08:52:11,978 INFO [decode.py:693] About to create model
+2024-01-16 08:52:12,576 INFO [decode.py:760] Calculating the averaged model over epoch range from 30 (excluded) to 40
+2024-01-16 08:52:22,828 INFO [decode.py:791] Number of model parameters: 65549011
+2024-01-16 08:52:22,829 INFO [asr_datamodule.py:371] About to get dev cuts
+2024-01-16 08:52:22,860 INFO [asr_datamodule.py:312] About to create dev dataset
+2024-01-16 08:52:23,509 INFO [asr_datamodule.py:329] About to create dev dataloader
+2024-01-16 08:52:23,510 INFO [asr_datamodule.py:376] About to get test cuts
+2024-01-16 08:52:23,512 INFO [asr_datamodule.py:341] About to create test dataset
+2024-01-16 08:52:25,546 INFO [decode.py:564] batch 0/?, cuts processed until now is 35
+2024-01-16 08:52:41,292 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.2616, 1.8791, 2.0020, 3.6743], device='cuda:0')
+2024-01-16 08:52:42,441 INFO [decode.py:564] batch 50/?, cuts processed until now is 2015
+2024-01-16 08:52:50,054 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([4.2876, 3.9804, 3.4153, 3.9264], device='cuda:0')
+2024-01-16 08:52:59,262 INFO [decode.py:564] batch 100/?, cuts processed until now is 4023
+2024-01-16 08:53:11,327 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([4.2526, 3.5149, 3.8873, 3.3463], device='cuda:0')
+2024-01-16 08:53:13,954 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.6640, 3.5339, 2.7571, 3.2975], device='cuda:0')
+2024-01-16 08:53:15,340 INFO [decode.py:564] batch 150/?, cuts processed until now is 6112
+2024-01-16 08:53:21,815 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.6251, 3.5824, 3.8278, 1.6666], device='cuda:0')
+2024-01-16 08:53:30,311 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.2507, 3.2402, 3.4456, 3.2989], device='cuda:0')
+2024-01-16 08:53:30,910 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([4.6706, 3.8788, 4.2342, 4.2799], device='cuda:0')
+2024-01-16 08:53:31,225 INFO [decode.py:564] batch 200/?, cuts processed until now is 8204
+2024-01-16 08:53:48,005 INFO [decode.py:564] batch 250/?, cuts processed until now is 10182
+2024-01-16 08:54:06,182 INFO [decode.py:564] batch 300/?, cuts processed until now is 12391
+2024-01-16 08:54:23,201 INFO [decode.py:564] batch 350/?, cuts processed until now is 14177
+2024-01-16 08:54:25,461 INFO [decode.py:580] The transcripts are stored in zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/greedy_search/recogs-dev-greedy_search_blank_penalty_0.0-epoch-40-avg-10-context-2-max-sym-per-frame-1-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 08:54:26,045 INFO [utils.py:565] [dev-greedy_search_blank_penalty_0.0] %WER 4.31% [8846 / 205341, 194 ins, 690 del, 7962 sub ]
+2024-01-16 08:54:26,887 INFO [decode.py:598] Wrote detailed error stats to zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/greedy_search/errs-dev-greedy_search_blank_penalty_0.0-epoch-40-avg-10-context-2-max-sym-per-frame-1-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 08:54:26,891 INFO [decode.py:614] 
+For dev, WER of different settings are:
+greedy_search_blank_penalty_0.0	4.31	best for dev
+
+2024-01-16 08:54:28,185 INFO [decode.py:564] batch 0/?, cuts processed until now is 31
+2024-01-16 08:54:46,025 INFO [decode.py:564] batch 50/?, cuts processed until now is 1797
+2024-01-16 08:55:03,919 INFO [decode.py:564] batch 100/?, cuts processed until now is 3578
+2024-01-16 08:55:11,697 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.0320, 1.9381, 2.6667, 1.9219, 2.6101, 2.3684, 2.6248, 2.4339],
+       device='cuda:0')
+2024-01-16 08:55:16,148 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.7322, 2.9529, 2.8860, 2.1513], device='cuda:0')
+2024-01-16 08:55:20,706 INFO [decode.py:564] batch 150/?, cuts processed until now is 5472
+2024-01-16 08:55:24,812 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([4.1918, 3.9201, 3.2397, 3.8215], device='cuda:0')
+2024-01-16 08:55:38,827 INFO [decode.py:564] batch 200/?, cuts processed until now is 7122
+2024-01-16 08:55:39,578 INFO [decode.py:580] The transcripts are stored in zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/greedy_search/recogs-test-greedy_search_blank_penalty_0.0-epoch-40-avg-10-context-2-max-sym-per-frame-1-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 08:55:39,835 INFO [utils.py:565] [test-greedy_search_blank_penalty_0.0] %WER 4.54% [4759 / 104765, 78 ins, 418 del, 4263 sub ]
+2024-01-16 08:55:40,266 INFO [decode.py:598] Wrote detailed error stats to zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/greedy_search/errs-test-greedy_search_blank_penalty_0.0-epoch-40-avg-10-context-2-max-sym-per-frame-1-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 08:55:40,269 INFO [decode.py:614] 
+For test, WER of different settings are:
+greedy_search_blank_penalty_0.0	4.54	best for test
+
+2024-01-16 08:55:40,280 INFO [decode.py:832] Done!

decoding_results/greedy_search/wer-summary-dev-greedy_search_blank_penalty_0.0-epoch-40-avg-10-context-2-max-sym-per-frame-1-blank-penalty-0.0-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search_blank_penalty_0.0	4.31

decoding_results/greedy_search/wer-summary-test-greedy_search_blank_penalty_0.0-epoch-40-avg-10-context-2-max-sym-per-frame-1-blank-penalty-0.0-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+greedy_search_blank_penalty_0.0	4.54

decoding_results/modified_beam_search/log-decode-epoch-40-avg-10-modified_beam_search-beam-size-4-blank-penalty-0.0-use-averaged-model-2024-01-16-10-03-43

@@ -0,0 +1,66 @@
+2024-01-16 10:03:43,643 INFO [decode.py:673] Decoding started
+2024-01-16 10:03:43,644 INFO [decode.py:679] Device: cuda:0
+2024-01-16 10:03:43,716 INFO [lexicon.py:168] Loading pre-compiled data/lang_bbpe_500/Linv.pt
+2024-01-16 10:03:43,728 INFO [decode.py:691] {'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': '1.24.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '2989b0b1186fa6022932804f5b39fbb2781ebf42', 'k2-git-date': 'Fri Nov 24 11:34:10 2023', 'lhotse-version': '1.19.0.dev+git.d1ae9c05.dirty', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev/aishell-zipformer-bbpe', 'icefall-git-sha1': 'bce81394-clean', 'icefall-git-date': 'Thu Jan 11 09:56:01 2024', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.4.dev20231207+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.19.0.dev0+git.d1ae9c05.dirty-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1207150822-75498b8c5f-55j4z', 'IP address': '10.177.74.211'}, 'epoch': 40, 'iter': 0, 'avg': 10, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan'), 'bpe_model': 'data/lang_bbpe_500/bbpe.model', 'lang_dir': PosixPath('data/lang_bbpe_500'), 'decoding_method': 'modified_beam_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'ilme_scale': 0.2, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'blank_penalty': 0.0, '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, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 200.0, '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, 'res_dir': PosixPath('zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/modified_beam_search'), 'suffix': 'epoch-40-avg-10-modified_beam_search-beam-size-4-blank-penalty-0.0-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
+2024-01-16 10:03:43,728 INFO [decode.py:693] About to create model
+2024-01-16 10:03:44,248 INFO [decode.py:760] Calculating the averaged model over epoch range from 30 (excluded) to 40
+2024-01-16 10:03:54,889 INFO [decode.py:791] Number of model parameters: 65549011
+2024-01-16 10:03:54,889 INFO [asr_datamodule.py:371] About to get dev cuts
+2024-01-16 10:03:54,905 INFO [asr_datamodule.py:312] About to create dev dataset
+2024-01-16 10:03:55,418 INFO [asr_datamodule.py:329] About to create dev dataloader
+2024-01-16 10:03:55,419 INFO [asr_datamodule.py:376] About to get test cuts
+2024-01-16 10:03:55,436 INFO [asr_datamodule.py:341] About to create test dataset
+2024-01-16 10:03:58,334 INFO [decode.py:564] batch 0/?, cuts processed until now is 35
+2024-01-16 10:04:28,300 INFO [decode.py:564] batch 20/?, cuts processed until now is 785
+2024-01-16 10:05:41,488 INFO [decode.py:564] batch 40/?, cuts processed until now is 1572
+2024-01-16 10:06:59,580 INFO [decode.py:564] batch 60/?, cuts processed until now is 2433
+2024-01-16 10:07:49,465 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.3113, 4.4908, 4.7379, 2.8855], device='cuda:0')
+2024-01-16 10:08:27,463 INFO [decode.py:564] batch 80/?, cuts processed until now is 3154
+2024-01-16 10:09:53,050 INFO [decode.py:564] batch 100/?, cuts processed until now is 4023
+2024-01-16 10:11:23,163 INFO [decode.py:564] batch 120/?, cuts processed until now is 4776
+2024-01-16 10:12:52,831 INFO [decode.py:564] batch 140/?, cuts processed until now is 5662
+2024-01-16 10:14:15,511 INFO [decode.py:564] batch 160/?, cuts processed until now is 6552
+2024-01-16 10:15:01,893 INFO [decode.py:564] batch 180/?, cuts processed until now is 7386
+2024-01-16 10:16:36,401 INFO [decode.py:564] batch 200/?, cuts processed until now is 8204
+2024-01-16 10:17:53,793 INFO [decode.py:564] batch 220/?, cuts processed until now is 8999
+2024-01-16 10:18:22,416 INFO [decode.py:564] batch 240/?, cuts processed until now is 9811
+2024-01-16 10:18:28,039 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([5.0271, 4.7459, 4.7175, 4.5908], device='cuda:0')
+2024-01-16 10:18:29,565 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.0997, 3.4467, 3.4164, 2.4607], device='cuda:0')
+2024-01-16 10:18:51,316 INFO [decode.py:564] batch 260/?, cuts processed until now is 10620
+2024-01-16 10:19:19,767 INFO [decode.py:564] batch 280/?, cuts processed until now is 11537
+2024-01-16 10:19:27,188 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.6404, 2.3883, 3.2457, 2.5336, 2.9562, 2.8679, 3.1428, 2.8781],
+       device='cuda:0')
+2024-01-16 10:19:48,713 INFO [decode.py:564] batch 300/?, cuts processed until now is 12391
+2024-01-16 10:20:18,251 INFO [decode.py:564] batch 320/?, cuts processed until now is 13152
+2024-01-16 10:20:47,711 INFO [decode.py:564] batch 340/?, cuts processed until now is 13879
+2024-01-16 10:21:08,641 INFO [decode.py:580] The transcripts are stored in zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/modified_beam_search/recogs-dev-beam_size_4_blank_penalty_0.0-epoch-40-avg-10-modified_beam_search-beam-size-4-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 10:21:09,092 INFO [utils.py:565] [dev-beam_size_4_blank_penalty_0.0] %WER 4.11% [8436 / 205341, 211 ins, 404 del, 7821 sub ]
+2024-01-16 10:21:09,789 INFO [decode.py:598] Wrote detailed error stats to zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/modified_beam_search/errs-dev-beam_size_4_blank_penalty_0.0-epoch-40-avg-10-modified_beam_search-beam-size-4-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 10:21:09,792 INFO [decode.py:614] 
+For dev, WER of different settings are:
+beam_size_4_blank_penalty_0.0	4.11	best for dev
+
+2024-01-16 10:21:12,237 INFO [decode.py:564] batch 0/?, cuts processed until now is 31
+2024-01-16 10:21:42,215 INFO [decode.py:564] batch 20/?, cuts processed until now is 697
+2024-01-16 10:22:11,516 INFO [decode.py:564] batch 40/?, cuts processed until now is 1395
+2024-01-16 10:23:08,740 INFO [decode.py:564] batch 60/?, cuts processed until now is 2169
+2024-01-16 10:23:10,319 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([4.8814, 4.2700, 4.5619, 3.9857], device='cuda:0')
+2024-01-16 10:23:38,833 INFO [decode.py:564] batch 80/?, cuts processed until now is 2801
+2024-01-16 10:24:07,941 INFO [decode.py:564] batch 100/?, cuts processed until now is 3578
+2024-01-16 10:24:37,343 INFO [decode.py:564] batch 120/?, cuts processed until now is 4249
+2024-01-16 10:25:01,661 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.9999, 1.6139, 2.6933, 2.7164, 2.7188, 2.4630, 2.3008, 2.6660],
+       device='cuda:0')
+2024-01-16 10:25:05,856 INFO [decode.py:564] batch 140/?, cuts processed until now is 5061
+2024-01-16 10:25:34,588 INFO [decode.py:564] batch 160/?, cuts processed until now is 5875
+2024-01-16 10:25:36,066 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([4.7714, 4.1238, 4.3947, 4.4562], device='cuda:0')
+2024-01-16 10:25:59,475 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.3344, 2.0402, 2.0603, 3.8063], device='cuda:0')
+2024-01-16 10:26:03,697 INFO [decode.py:564] batch 180/?, cuts processed until now is 6581
+2024-01-16 10:26:27,635 INFO [decode.py:564] batch 200/?, cuts processed until now is 7122
+2024-01-16 10:26:30,390 INFO [decode.py:580] The transcripts are stored in zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/modified_beam_search/recogs-test-beam_size_4_blank_penalty_0.0-epoch-40-avg-10-modified_beam_search-beam-size-4-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 10:26:30,610 INFO [utils.py:565] [test-beam_size_4_blank_penalty_0.0] %WER 4.37% [4583 / 104765, 96 ins, 262 del, 4225 sub ]
+2024-01-16 10:26:30,971 INFO [decode.py:598] Wrote detailed error stats to zipformer_bbpe/exp-context-size-2-lr-epochs-10-spec-aug-20-disable-musan/modified_beam_search/errs-test-beam_size_4_blank_penalty_0.0-epoch-40-avg-10-modified_beam_search-beam-size-4-blank-penalty-0.0-use-averaged-model.txt
+2024-01-16 10:26:30,974 INFO [decode.py:614] 
+For test, WER of different settings are:
+beam_size_4_blank_penalty_0.0	4.37	best for test
+
+2024-01-16 10:26:30,982 INFO [decode.py:832] Done!

decoding_results/modified_beam_search/wer-summary-dev-beam_size_4_blank_penalty_0.0-epoch-40-avg-10-modified_beam_search-beam-size-4-blank-penalty-0.0-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_size_4_blank_penalty_0.0	4.11

decoding_results/modified_beam_search/wer-summary-test-beam_size_4_blank_penalty_0.0-epoch-40-avg-10-modified_beam_search-beam-size-4-blank-penalty-0.0-use-averaged-model.txt

@@ -0,0 +1,2 @@
+settings	WER
+beam_size_4_blank_penalty_0.0	4.37

exp/.gitattributes

@@ -0,0 +1,6 @@
+encoder-epoch-40-avg-10.onnx filter=lfs diff=lfs merge=lfs -text
+joiner-epoch-40-avg-10.int8.onnx filter=lfs diff=lfs merge=lfs -text
+joiner-epoch-40-avg-10.onnx filter=lfs diff=lfs merge=lfs -text
+decoder-epoch-40-avg-10.int8.onnx filter=lfs diff=lfs merge=lfs -text
+decoder-epoch-40-avg-10.onnx filter=lfs diff=lfs merge=lfs -text
+encoder-epoch-40-avg-10.int8.onnx filter=lfs diff=lfs merge=lfs -text

exp/decoder-epoch-40-avg-10.int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28af835100c308c054995a2796658ad8ed6688e9d282a66525ad138383f6b3ae
+size 540158

exp/decoder-epoch-40-avg-10.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13cc842bbe5dd0a78c0a9537a0a1204546a8c402be7542a8d4346b8058c025b
+size 2093097

exp/encoder-epoch-40-avg-10.int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86466a93b311ae97c682714dcc4ad2f950f46868f64be11a23c9a3d0f2364769
+size 69037476

exp/encoder-epoch-40-avg-10.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74bd4c3c37c4a5e3a23eef5f482594754d72340ea6e6d670e9739955e439e92
+size 260000054

exp/epoch-40.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3fb2f75b80dbef47d4d352f2d35487e915476fccabbba67842afda99ba812c
+size 1049765648

exp/jit_script.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9df2da8fee40df1e0161716b63d1736cd9d1447994eea196bbaa47f05cf7cb
+size 264930494

exp/joiner-epoch-40-avg-10.int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dde9191d647df89d65afb68b7d9105d8820dfcfee9583482e1f4d04442cf135
+size 259479

exp/joiner-epoch-40-avg-10.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af6e5d7b8d589a84c6252c3db33b2e94eb84ba05d81b56f435599a20891a4c8
+size 1026451

exp/pretrained.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:890aa98194100fb1edf6f5475c16688c7f6e1a3e059f522d87e221c5bec59976
+size 262602995

exp/tensorboard/events.out.tfevents.1705288061.de-74279-k2-train-1-1207150822-75498b8c5f-55j4z.2432177.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111733bf4d146be7b42f554de45c111b3281473bfca0404c492c4f41bda10724
+size 332370