txya900619 commited on
Commit
8b2fe6b
1 Parent(s): 6ff48ca

Upload tokenizer.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer.json +576 -644
tokenizer.json CHANGED
@@ -54,251 +54,251 @@
54
  "_": 8,
55
  "a": 9,
56
  "b": 10,
57
- "e": 11,
58
- "f": 12,
59
- "h": 13,
60
- "i": 14,
61
- "k": 15,
62
- "l": 16,
63
- "m": 17,
64
- "n": 18,
65
- "o": 19,
66
- "p": 20,
67
- "s": 21,
68
- "t": 22,
69
- "u": 23,
70
- "v": 24,
71
- "ŋ": 25,
72
- "ɕ": 26,
73
- "ɛ": 27,
74
- "ɨ": 28,
75
- "ʊ": 29,
76
- "ʰ": 30,
77
- "̩": 31,
78
- "͡": 32,
79
- "_5": 33,
80
- "_55": 34,
81
- "_2": 35,
82
- "_24": 36,
83
- "11": 37,
84
- "_11": 38,
85
- "31": 39,
86
- "_31": 40,
87
- "_55 ": 41,
88
- "": 42,
89
- "i_55": 43,
90
- "t͡s": 44,
91
- "_24 ": 45,
92
- "_11 ": 46,
93
- "_31 ": 47,
94
- "": 48,
95
- "t_2": 49,
96
- "": 50,
97
- "i_24": 51,
98
- "e_55 ": 52,
99
- "i_11": 53,
100
- "en": 54,
101
- "t͡ɕ": 55,
102
- "i_55 ": 56,
103
- "in": 57,
104
- "i_31": 58,
105
- "o_55": 59,
106
- "ke_55 ": 60,
107
- "": 61,
108
- "t͡sʰ": 62,
109
- "t͡ɕʰ": 63,
110
- "a_55": 64,
111
- "": 65,
112
- "u_55": 66,
113
- "k_2": 67,
114
- "": 68,
115
- "a_24": 69,
116
- "": 70,
117
- "an": 71,
118
- "e_55": 72,
119
- "it_2": 73,
120
- "i_11 ": 74,
121
- "o_11": 75,
122
- "u_24": 76,
123
- "un": 77,
124
- "on": 78,
125
- "to": 79,
126
- "e_31": 80,
127
- "et_2": 81,
128
- "t_5": 82,
129
- "a_31": 83,
130
- "u_31": 84,
131
- "u_24 ": 85,
132
- "": 86,
133
- "o_55i_55 ": 87,
134
- "u_55 ": 88,
135
- "a_11": 89,
136
- "am": 90,
137
- "ŋin": 91,
138
- "t͡ɕʰi_55": 92,
139
- "k_5": 93,
140
- "i_2": 94,
141
- "a_24 ": 95,
142
- "u_11": 96,
143
- "̩_11": 97,
144
- "ak_2": 98,
145
- "o_31": 99,
146
- "e_24": 100,
147
- "e_31 ": 101,
148
- "i_11en": 102,
149
- "m̩_11": 103,
150
- "e_11": 104,
151
- "lo_11": 105,
152
- "a_55i_55": 106,
153
- "oŋ_24": 107,
154
- "oŋ_31": 108,
155
- "he_55 ": 109,
156
- "uk_2": 110,
157
- "uŋ_24": 111,
158
- "o_24": 112,
159
- "en_24": 113,
160
- "ke_55": 114,
161
- "i_24 ": 115,
162
- "ki_24": 116,
163
- "ŋa_11": 117,
164
- "i_55en": 118,
165
- "p_5": 119,
166
- "i_5": 120,
167
- "a_55 ": 121,
168
- "ki_11 ": 122,
169
- "et_2 ": 123,
170
- "oŋ_55": 124,
171
- "ok_5": 125,
172
- "ŋin_11": 126,
173
- "_24": 127,
174
- "i_24u_24 ": 128,
175
- "u_31 ": 129,
176
- "i_31 ": 130,
177
- "o_55i_55": 131,
178
- "it_2 ": 132,
179
- "tʰuŋ": 133,
180
- "oŋ_55 ": 134,
181
- "to_55 ": 135,
182
- "im": 136,
183
- "tʰe_11": 137,
184
- "i_11en_11": 138,
185
- "ŋin_11 ": 139,
186
- "t͡sɨ": 140,
187
- "ok_2": 141,
188
- "mo_11": 142,
189
- "vo_55i_55 ": 143,
190
- "o_31 ": 144,
191
- "ŋa_11i_11 ": 145,
192
- "o_55 ": 146,
193
- "sɨt_5": 147,
194
- "i_55en_55": 148,
195
- "ti_55 ": 149,
196
- "han": 150,
197
- "ten": 151,
198
- "lo_11i_11 ": 152,
199
- "tʰa_55i_55": 153,
200
- "to_31 ": 154,
201
- "t͡ɕʰi_55u_55 ": 155,
202
- "oŋ_11": 156,
203
- "ut_2": 157,
204
- "t͡ɕʰin": 158,
205
- "ak_2 ": 159,
206
- "oŋ_24 ": 160,
207
- "i_31a_31": 161,
208
- "t͡so_55": 162,
209
- "a_31 ": 163,
210
- "kin": 164,
211
- "u_11 ": 165,
212
- "pun": 166,
213
- "se_55": 167,
214
- "an_24": 168,
215
- "et_5": 169,
216
- "on_55": 170,
217
- "te_24": 171,
218
- "o_11 ": 172,
219
- "i_31oŋ_31": 173,
220
- "ŋ̩": 174,
221
- "su_31": 175,
222
- "oŋ_31 ": 176,
223
- "aŋ_11": 177,
224
- "tʰe_11u_11": 178,
225
- "i_11en_11 ": 179,
226
- "i_31a_31 ": 180,
227
- "a_55i_55 ": 181,
228
- "t͡ɕʰi_55u_55": 182,
229
- "p_2": 183,
230
- "aŋ_55": 184,
231
- "lo_11i_11": 185,
232
- "i_2et_2": 186,
233
- "i_24en_24": 187,
234
- "i_55uŋ": 188,
235
- "ho_31": 189,
236
- "koŋ_31": 190,
237
- "sɨn": 191,
238
- "he_55": 192,
239
- "am_24": 193,
240
- "at_2": 194,
241
- "hi_55 ": 195,
242
- "ap_5": 196,
243
- "i_55a_55": 197,
244
- "ten_31 ": 198,
245
- "i_24u_24": 199,
246
- "on_24": 200,
247
- "t͡sʰut_2": 201,
248
- "en_24 ": 202,
249
- "t͡sʰɨ": 203,
250
- "an_31": 204,
251
- "t͡suŋ": 205,
252
- "im_24": 206,
253
- "ki_31": 207,
254
- "ko_55": 208,
255
- "te_24u_24 ": 209,
256
- "aŋ_24 ": 210,
257
- "ho_31 ": 211,
258
- "ka_24": 212,
259
- "ŋi_11": 213,
260
- "tet_2 ": 214,
261
- "an_55": 215,
262
- "ki_11": 216,
263
- "ka_24 ": 217,
264
- "tu_55": 218,
265
- "sɨ_55": 219,
266
- "ŋ̩_11 ": 220,
267
- "oŋ_11 ": 221,
268
- "i_5et_5": 222,
269
- "han_11": 223,
270
- "kʰon_55": 224,
271
- "ɕi_24": 225,
272
- "sɨ_11": 226,
273
- "in_24": 227,
274
- "ap_2": 228,
275
- "ko_55 ": 229,
276
- "ha_24": 230,
277
- "ti_24": 231,
278
- "in_55": 232,
279
- "kʰi_11": 233,
280
- "uk_5": 234,
281
- "i_55oŋ_55": 235,
282
- "li_11": 236,
283
- "mo_11 ": 237,
284
- "ki_2": 238,
285
- "uŋ_11": 239,
286
- "e_31u_31": 240,
287
- "ki_55": 241,
288
- "un_11": 242,
289
- "tʰuŋ_11 ": 243,
290
- "hi_55": 244,
291
- "i_31en": 245,
292
- "t͡sak_2 ": 246,
293
- "toŋ_24": 247,
294
- "saŋ_24": 248,
295
  "ku_24": 249,
296
- "vuk_2": 250,
297
- "e_24u_24": 251,
298
- "aŋ_55 ": 252,
299
- "e_55u_55": 253,
300
- "pun_24 ": 254,
301
- "pa_31": 255
302
  },
303
  "merges": [
304
  [
@@ -341,10 +341,6 @@
341
  "t",
342
  "͡"
343
  ],
344
- [
345
- "i",
346
- "_55"
347
- ],
348
  [
349
  "t͡",
350
  "s"
@@ -353,6 +349,10 @@
353
  "_24",
354
  " "
355
  ],
 
 
 
 
356
  [
357
  "_11",
358
  " "
@@ -361,42 +361,42 @@
361
  "_31",
362
  " "
363
  ],
364
- [
365
- "o",
366
- "ŋ"
367
- ],
368
  [
369
  "t",
370
- "_2"
371
  ],
372
  [
373
  "t",
374
- "ʰ"
375
  ],
376
  [
377
  "i",
378
  "_24"
379
  ],
380
- [
381
- "e",
382
- "_55 "
383
- ],
384
  [
385
  "i",
386
  "_11"
387
  ],
 
 
 
 
388
  [
389
  "e",
390
  "n"
391
  ],
392
  [
393
- "",
394
- "ɕ"
395
  ],
396
  [
397
- "i",
398
  "_55 "
399
  ],
 
 
 
 
400
  [
401
  "i",
402
  "n"
@@ -406,32 +406,32 @@
406
  "_31"
407
  ],
408
  [
409
- "o",
410
- "_55"
411
  ],
412
  [
413
- "k",
414
- "e_55 "
415
  ],
416
  [
417
- "u",
418
- "ŋ"
419
  ],
420
  [
421
- "t͡s",
422
- "ʰ"
423
  ],
424
  [
425
- "t͡ɕ",
426
  "ʰ"
427
  ],
428
  [
429
- "a",
430
- "_55"
431
  ],
432
  [
433
  "a",
434
- "ŋ"
435
  ],
436
  [
437
  "u",
@@ -441,33 +441,33 @@
441
  "k",
442
  "_2"
443
  ],
444
- [
445
- "s",
446
- "ɨ"
447
- ],
448
  [
449
  "a",
450
- "_24"
451
  ],
452
  [
453
- "k",
454
  "ʰ"
455
  ],
456
  [
457
  "a",
458
- "n"
459
  ],
460
  [
461
- "e",
462
- "_55"
463
  ],
464
  [
465
- "i",
466
- "t_2"
467
  ],
468
  [
469
- "i",
470
- "_11 "
 
 
 
 
471
  ],
472
  [
473
  "o",
@@ -479,719 +479,651 @@
479
  ],
480
  [
481
  "u",
482
- "n"
483
  ],
484
  [
485
- "o",
486
- "n"
487
  ],
488
  [
489
- "t",
490
- "o"
491
  ],
492
  [
493
  "e",
494
- "_31"
495
  ],
496
  [
497
- "e",
498
- "t_2"
499
  ],
500
  [
501
- "t",
502
- "_5"
503
  ],
504
  [
505
- "a",
506
- "_31"
507
  ],
508
  [
509
  "u",
510
  "_31"
511
  ],
512
  [
513
- "u",
514
- "_24 "
515
- ],
516
- [
517
- "p",
518
- "ʰ"
519
  ],
520
  [
521
  "o_55",
522
  "i_55 "
523
  ],
524
  [
525
- "u",
526
- "_55 "
527
  ],
528
  [
529
  "a",
530
- "_11"
531
  ],
532
  [
533
- "a",
534
- "m"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
535
  ],
536
  [
537
  "ŋ",
538
  "in"
539
  ],
540
  [
541
- "t͡ɕʰ",
542
- "i_55"
543
  ],
544
  [
545
- "k",
546
- "_5"
547
  ],
548
  [
549
- "i",
550
- "_2"
551
  ],
552
  [
553
  "a",
554
  "_24 "
555
  ],
556
  [
557
- "u",
558
- "_11"
559
  ],
560
  [
561
- "̩",
562
- "_11"
563
  ],
564
  [
565
- "a",
566
- "k_2"
567
  ],
568
  [
569
- "o",
570
- "_31"
 
 
 
 
571
  ],
572
  [
573
  "e",
574
  "_24"
575
  ],
 
 
 
 
576
  [
577
  "e",
578
- "_31 "
579
  ],
580
  [
581
- "i_11",
582
- "en"
583
  ],
584
  [
585
- "m",
586
- "̩_11"
587
  ],
588
  [
589
- "e",
590
- "_11"
591
  ],
592
  [
593
  "l",
594
  "o_11"
595
  ],
596
  [
597
- "a_55",
598
- "i_55"
599
- ],
600
- [
601
- "oŋ",
602
- "_24"
603
  ],
604
  [
605
- "",
606
- "_31"
607
  ],
608
  [
609
  "h",
610
  "e_55 "
611
  ],
612
  [
613
- "u",
614
- "k_2"
615
- ],
616
- [
617
- "uŋ",
618
- "_24"
619
  ],
620
  [
621
- "o",
622
- "_24"
623
  ],
624
  [
625
- "en",
626
- "_24"
627
  ],
628
  [
629
- "k",
630
- "e_55"
631
  ],
632
  [
633
- "i",
634
- "_24 "
635
  ],
636
  [
637
- "k",
638
- "i_24"
639
  ],
640
  [
641
- "ŋ",
642
- "a_11"
643
  ],
644
  [
645
- "i_55",
646
- "en"
647
  ],
648
  [
649
- "p",
650
- "_5"
651
  ],
652
  [
653
  "i",
654
- "_5"
655
  ],
656
  [
657
  "a",
658
  "_55 "
659
  ],
660
  [
661
- "k",
662
- "i_11 "
663
  ],
664
  [
665
- "et_2",
666
- " "
667
  ],
668
  [
669
- "",
670
- "_55"
671
  ],
672
  [
673
- "o",
674
- "k_5"
675
- ],
676
- [
677
- "ŋin",
678
- "_11"
679
- ],
680
- [
681
- "aŋ",
682
  "_24"
683
  ],
684
  [
685
- "i_24",
686
- "u_24 "
687
- ],
688
- [
689
- "u",
690
- "_31 "
691
- ],
692
- [
693
- "i",
694
- "_31 "
695
- ],
696
- [
697
- "o_55",
698
- "i_55"
699
- ],
700
- [
701
- "it_2",
702
- " "
703
  ],
704
  [
705
- "",
706
- ""
707
  ],
708
  [
709
  "oŋ",
710
  "_55 "
711
  ],
712
  [
713
- "to",
714
- "_55 "
715
- ],
716
- [
717
- "i",
718
- "m"
719
- ],
720
- [
721
- "tʰ",
722
- "e_11"
723
  ],
724
  [
725
  "i_11en",
726
  "_11"
727
  ],
728
- [
729
- "ŋin",
730
- "_11 "
731
- ],
732
- [
733
- "t͡s",
734
- "ɨ"
735
- ],
736
- [
737
- "o",
738
- "k_2"
739
- ],
740
- [
741
- "m",
742
- "o_11"
743
- ],
744
  [
745
  "v",
746
  "o_55i_55 "
747
  ],
748
  [
749
- "o",
750
- "_31 "
751
  ],
752
  [
753
- "ŋa_11",
754
- "i_11 "
755
  ],
756
  [
757
- "o",
758
  "_55 "
759
  ],
760
  [
761
- "",
762
- "t_5"
763
- ],
764
- [
765
- "i_55en",
766
- "_55"
767
  ],
768
  [
769
  "t",
770
  "i_55 "
771
  ],
772
  [
773
- "h",
774
- "an"
775
- ],
776
- [
777
- "t",
778
- "en"
779
- ],
780
- [
781
- "lo_11",
782
- "i_11 "
783
  ],
784
  [
785
- "",
786
- "a_55i_55"
787
  ],
788
  [
789
- "to",
790
- "_31 "
791
  ],
792
  [
793
- "t͡ɕʰi_55",
794
- "u_55 "
795
  ],
796
  [
797
  "oŋ",
798
- "_11"
799
- ],
800
- [
801
- "u",
802
- "t_2"
803
- ],
804
- [
805
- "t͡ɕʰ",
806
- "in"
807
  ],
808
  [
809
- "ak_2",
810
- " "
811
  ],
812
  [
813
  "oŋ",
814
  "_24 "
815
  ],
816
  [
817
- "i_31",
818
- "a_31"
819
  ],
820
  [
821
- "t͡s",
822
- "o_55"
823
  ],
824
  [
825
  "a",
826
- "_31 "
827
  ],
828
  [
829
- "k",
830
- "in"
831
  ],
832
  [
833
- "u",
834
- "_11 "
835
  ],
836
  [
837
- "p",
838
- "un"
839
  ],
840
  [
841
- "s",
842
- "e_55"
843
  ],
844
  [
845
- "an",
846
- "_24"
847
  ],
848
  [
849
- "e",
850
- "t_5"
851
  ],
852
  [
853
- "on",
854
- "_55"
855
  ],
856
  [
857
- "t",
858
- "e_24"
859
  ],
860
  [
861
- "o",
862
- "_11 "
863
  ],
864
  [
865
  "i_31",
866
- "oŋ_31"
867
- ],
868
- [
869
- "ŋ",
870
- "̩"
871
- ],
872
- [
873
- "s",
874
- "u_31"
875
  ],
876
  [
877
- "",
878
- "_31 "
879
  ],
880
  [
881
- "",
882
- "_11"
883
  ],
884
  [
885
- "tʰe_11",
886
- "u_11"
887
  ],
888
  [
889
- "i_11en",
890
- "_11 "
891
  ],
892
  [
893
- "i_31",
894
- "a_31 "
895
  ],
896
  [
897
- "a_55",
898
- "i_55 "
899
  ],
900
  [
901
- "t͡ɕʰi_55",
902
- "u_55"
903
  ],
904
  [
905
- "p",
906
- "_2"
907
  ],
908
  [
909
- "",
910
  "_55"
911
  ],
912
  [
913
- "lo_11",
914
- "i_11"
915
  ],
916
  [
917
- "i_2",
918
- "et_2"
919
  ],
920
  [
921
- "i_24",
922
- "en_24"
923
  ],
924
  [
925
- "i_55",
926
- ""
927
  ],
928
  [
929
- "h",
930
- "o_31"
931
  ],
932
  [
933
  "k",
934
- "oŋ_31"
935
- ],
936
- [
937
- "sɨ",
938
- "n"
939
- ],
940
- [
941
- "h",
942
- "e_55"
943
  ],
944
  [
945
- "am",
946
  "_24"
947
  ],
948
  [
949
  "a",
950
- "t_2"
951
- ],
952
- [
953
- "h",
954
- "i_55 "
955
  ],
956
  [
957
- "a",
958
- "p_5"
959
  ],
960
  [
961
- "i_55",
962
- "a_55"
963
  ],
964
  [
965
- "ten",
966
- "_31 "
967
  ],
968
  [
969
- "i_24",
970
- "u_24"
971
  ],
972
  [
973
- "on",
974
- "_24"
975
  ],
976
  [
977
- "t͡sʰ",
978
- "ut_2"
979
  ],
980
  [
981
- "en",
982
- "_24 "
983
  ],
984
  [
985
- "t͡sʰ",
986
- "ɨ"
987
  ],
988
  [
989
- "an",
990
- "_31"
991
  ],
992
  [
993
- "t͡s",
994
- ""
995
  ],
996
  [
997
- "im",
998
- "_24"
999
  ],
1000
  [
1001
  "k",
1002
- "i_31"
1003
  ],
1004
  [
1005
- "k",
1006
- "o_55"
1007
  ],
1008
  [
1009
- "te_24",
1010
- "u_24 "
1011
  ],
1012
  [
1013
- "",
1014
- "_24 "
1015
  ],
1016
  [
1017
- "h",
1018
- "o_31 "
1019
  ],
1020
  [
1021
  "k",
1022
  "a_24"
1023
  ],
1024
  [
1025
- "ŋ",
1026
- "i_11"
1027
  ],
1028
  [
1029
- "t",
1030
- "et_2 "
1031
  ],
1032
  [
1033
  "an",
1034
- "_55"
1035
  ],
1036
  [
1037
- "k",
1038
  "i_11"
1039
  ],
1040
  [
1041
- "k",
1042
- "a_24 "
1043
- ],
1044
- [
1045
- "t",
1046
- "u_55"
1047
  ],
1048
  [
1049
- "",
1050
- "_55"
1051
  ],
1052
  [
1053
- "ŋ̩",
1054
- "_11 "
1055
  ],
1056
  [
1057
- "",
1058
- "_11 "
1059
  ],
1060
  [
1061
- "i_5",
1062
- "et_5"
1063
  ],
1064
  [
1065
- "han",
1066
- "_11"
1067
  ],
1068
  [
1069
- "",
1070
- "on_55"
1071
  ],
1072
  [
1073
- "ɕ",
1074
- "i_24"
1075
  ],
1076
  [
1077
- "",
1078
- "_11"
1079
  ],
1080
  [
1081
- "in",
1082
  "_24"
1083
  ],
1084
  [
1085
- "a",
1086
- "p_2"
1087
  ],
1088
  [
1089
- "k",
1090
- "o_55 "
1091
  ],
1092
  [
1093
- "h",
1094
- "a_24"
1095
  ],
1096
  [
1097
- "t",
1098
- "i_24"
1099
  ],
1100
  [
1101
- "in",
1102
- "_55"
1103
  ],
1104
  [
1105
- "",
1106
- "i_11"
1107
  ],
1108
  [
1109
- "u",
1110
- "k_5"
1111
  ],
1112
  [
1113
- "i_55",
1114
- "oŋ_55"
1115
  ],
1116
  [
1117
- "l",
1118
- "i_11"
1119
  ],
1120
  [
1121
- "m",
1122
- "o_11 "
1123
  ],
1124
  [
1125
- "k",
1126
- "i_2"
1127
  ],
1128
  [
1129
- "",
1130
- "_11"
1131
  ],
1132
  [
1133
- "e_31",
1134
- "u_31"
1135
  ],
1136
  [
1137
- "k",
1138
  "i_55"
1139
  ],
1140
  [
1141
- "un",
1142
- "_11"
1143
  ],
1144
  [
1145
  "tʰuŋ",
1146
  "_11 "
1147
  ],
1148
  [
1149
- "h",
1150
- "i_55"
1151
  ],
1152
  [
1153
- "i_31",
1154
- "en"
 
 
 
 
1155
  ],
1156
  [
1157
  "t͡s",
1158
- "ak_2 "
1159
  ],
1160
  [
1161
- "t",
1162
- "oŋ_24"
1163
  ],
1164
  [
1165
- "s",
1166
- "aŋ_24"
1167
  ],
1168
  [
1169
- "k",
1170
- "u_24"
1171
  ],
1172
  [
1173
- "v",
1174
- "uk_2"
1175
  ],
1176
  [
1177
- "e_24",
1178
  "u_24"
1179
  ],
1180
  [
1181
  "aŋ",
1182
- "_55 "
1183
  ],
1184
  [
1185
- "e_55",
1186
- "u_55"
1187
  ],
1188
  [
1189
- "pun",
1190
- "_24 "
1191
  ],
1192
  [
1193
- "p",
1194
- "a_31"
 
 
 
 
1195
  ]
1196
  ]
1197
  }
 
54
  "_": 8,
55
  "a": 9,
56
  "b": 10,
57
+ "d": 11,
58
+ "e": 12,
59
+ "f": 13,
60
+ "h": 14,
61
+ "i": 15,
62
+ "j": 16,
63
+ "k": 17,
64
+ "l": 18,
65
+ "m": 19,
66
+ "n": 20,
67
+ "o": 21,
68
+ "p": 22,
69
+ "s": 23,
70
+ "t": 24,
71
+ "u": 25,
72
+ "v": 26,
73
+ "w": 27,
74
+ "z": 28,
75
+ "æ": 29,
76
+ "ð": 30,
77
+ "ŋ": 31,
78
+ "ɑ": 32,
79
+ "ɔ": 33,
80
+ "ɕ": 34,
81
+ "ə": 35,
82
+ "ɚ": 36,
83
+ "ɛ": 37,
84
+ "ɡ": 38,
85
+ "ɨ": 39,
86
+ "ɪ": 40,
87
+ "ɹ": 41,
88
+ "ʃ": 42,
89
+ "ʊ": 43,
90
+ "ʌ": 44,
91
+ "ʒ": 45,
92
+ "ʰ": 46,
93
+ "̩": 47,
94
+ "͡": 48,
95
+ "θ": 49,
96
+ "_5": 50,
97
+ "_55": 51,
98
+ "_2": 52,
99
+ "_24": 53,
100
+ "11": 54,
101
+ "_11": 55,
102
+ "31": 56,
103
+ "_31": 57,
104
+ "_55 ": 58,
105
+ "": 59,
106
+ "t͡s": 60,
107
+ "_24 ": 61,
108
+ "i_55": 62,
109
+ "_11 ": 63,
110
+ "_31 ": 64,
111
+ "": 65,
112
+ "t_2": 66,
113
+ "i_24": 67,
114
+ "i_11": 68,
115
+ "": 69,
116
+ "en": 70,
117
+ "i_55 ": 71,
118
+ "e_55 ": 72,
119
+ "": 73,
120
+ "in": 74,
121
+ "i_31": 75,
122
+ "t͡sʰ": 76,
123
+ "": 77,
124
+ "t͡ɕ": 78,
125
+ "o_55": 79,
126
+ "": 80,
127
+ "ke_55 ": 81,
128
+ "an": 82,
129
+ "u_55": 83,
130
+ "k_2": 84,
131
+ "": 85,
132
+ "t͡ɕʰ": 86,
133
+ "a_55": 87,
134
+ "t_2 ": 88,
135
+ "a_24": 89,
136
+ "un": 90,
137
+ "_5 ": 91,
138
+ "o_11": 92,
139
+ "u_24": 93,
140
+ "u_55 ": 94,
141
+ "am": 95,
142
+ "u_24 ": 96,
143
+ "e_55": 97,
144
+ "": 98,
145
+ "on": 99,
146
+ "i_11 ": 100,
147
+ "u_31": 101,
148
+ "to": 102,
149
+ "o_55i_55 ": 103,
150
+ "i_11en": 104,
151
+ "a_31": 105,
152
+ "it_2": 106,
153
+ "i_2": 107,
154
+ "e_31": 108,
155
+ "i_5": 109,
156
+ "uŋ_24": 110,
157
+ "k_2 ": 111,
158
+ "ŋin": 112,
159
+ "t͡sɨ": 113,
160
+ "i_55en": 114,
161
+ "ho": 115,
162
+ "a_24 ": 116,
163
+ "et_2 ": 117,
164
+ "i_24 ": 118,
165
+ "t_5": 119,
166
+ "ko": 120,
167
+ "a_11": 121,
168
+ "e_24": 122,
169
+ "u_11": 123,
170
+ "et_2": 124,
171
+ "tʰuŋ": 125,
172
+ "ap": 126,
173
+ "_24": 127,
174
+ "lo_11": 128,
175
+ "k_5": 129,
176
+ "a_55i_55": 130,
177
+ "he_55 ": 131,
178
+ "i_24u_24 ": 132,
179
+ "oŋ_31": 133,
180
+ "u_31 ": 134,
181
+ "t͡ɕʰi_55": 135,
182
+ "i_24en": 136,
183
+ "t_5 ": 137,
184
+ "it_2 ": 138,
185
+ "i_11en_11 ": 139,
186
+ "im": 140,
187
+ "i_31 ": 141,
188
+ "a_55 ": 142,
189
+ "e_31 ": 143,
190
+ "̩_11": 144,
191
+ "e_11": 145,
192
+ "in_24": 146,
193
+ "m̩_11": 147,
194
+ "sɨp": 148,
195
+ "oŋ_55 ": 149,
196
+ "i_55en_55": 150,
197
+ "i_11en_11": 151,
198
+ "vo_55i_55 ": 152,
199
+ "k_5 ": 153,
200
+ "an_11": 154,
201
+ "to_55 ": 155,
202
+ "o_24": 156,
203
+ "ti_55 ": 157,
204
+ "uk_2": 158,
205
+ "ki_24": 159,
206
+ "u_11 ": 160,
207
+ "ke_55": 161,
208
+ "oŋ_55": 162,
209
+ "oŋ_31 ": 163,
210
+ "oŋ_24 ": 164,
211
+ "sɨ_55": 165,
212
+ "o_55i_55": 166,
213
+ "ak_2": 167,
214
+ "o_31": 168,
215
+ "ŋin_11": 169,
216
+ "lo_11i_11 ": 170,
217
+ "ŋin_11 ": 171,
218
+ "tʰa_55i_55": 172,
219
+ "tʰo_11": 173,
220
+ "aŋ_24": 174,
221
+ "ŋi_5": 175,
222
+ "ak_2 ": 176,
223
+ "i_31a_31": 177,
224
+ "uŋ_24 ": 178,
225
+ "i_55uŋ": 179,
226
+ "sɨn": 180,
227
+ "to_31 ": 181,
228
+ "t͡so_55": 182,
229
+ "t͡sʰɨ": 183,
230
+ "ŋ̩": 184,
231
+ "in_11": 185,
232
+ "in_55": 186,
233
+ "i_55en_55 ": 187,
234
+ i_55": 188,
235
+ "oŋ_11 ": 189,
236
+ "sɨp_5": 190,
237
+ "oŋ_11": 191,
238
+ "ki_31": 192,
239
+ "i_24en_24": 193,
240
+ "a_31 ": 194,
241
+ "aŋ_11": 195,
242
+ "am_24": 196,
243
+ "tʰe_11": 197,
244
+ "ten": 198,
245
+ "t͡sʰu": 199,
246
+ "han_11": 200,
247
+ "pun": 201,
248
+ "at_2": 202,
249
+ "a_55i_55 ": 203,
250
+ "ki_11 ": 204,
251
+ "u_55i_55 ": 205,
252
+ "ku": 206,
253
+ "i_31oŋ_31": 207,
254
+ "e_24u_24": 208,
255
+ "e_31u_31": 209,
256
+ "an_24": 210,
257
+ "ka_24": 211,
258
+ "ka_24 ": 212,
259
+ "i_11": 213,
260
+ "an_24 ": 214,
261
+ "tʰo_11i_11": 215,
262
+ "mo_11": 216,
263
+ "ki_55": 217,
264
+ "ku_2": 218,
265
+ "ko_55 ": 219,
266
+ "ŋa_11": 220,
267
+ "e_55u_55": 221,
268
+ "t͡sɨn": 222,
269
+ "t͡so": 223,
270
+ "kin": 224,
271
+ "im_24": 225,
272
+ "ŋi_11en_11 ": 226,
273
+ "e_24u_24 ": 227,
274
+ "tet_2 ": 228,
275
+ "i_24en_24 ": 229,
276
+ "ip": 230,
277
+ "on_24": 231,
278
+ "un_11": 232,
279
+ "kuŋ_24": 233,
280
+ "su_31": 234,
281
+ "ap_2": 235,
282
+ "sɨ_55 ": 236,
283
+ "aŋ_11 ": 237,
284
+ "on_55": 238,
285
+ "tʰi_55": 239,
286
+ "et_5 ": 240,
287
+ "tʰuŋ_11 ": 241,
288
+ "an_55": 242,
289
+ "o_11 ": 243,
290
+ "uk_2 ": 244,
291
+ "t͡suŋ": 245,
292
+ "ho_31": 246,
293
+ "i_2et_2": 247,
294
+ "i_31en": 248,
295
  "ku_24": 249,
296
+ "i_24u_24": 250,
297
+ "aŋ_55": 251,
298
+ "ŋi_11": 252,
299
+ "an_55 ": 253,
300
+ "an_31": 254,
301
+ "hi_55 ": 255
302
  },
303
  "merges": [
304
  [
 
341
  "t",
342
  "͡"
343
  ],
 
 
 
 
344
  [
345
  "t͡",
346
  "s"
 
349
  "_24",
350
  " "
351
  ],
352
+ [
353
+ "i",
354
+ "_55"
355
+ ],
356
  [
357
  "_11",
358
  " "
 
361
  "_31",
362
  " "
363
  ],
 
 
 
 
364
  [
365
  "t",
366
+ "ʰ"
367
  ],
368
  [
369
  "t",
370
+ "_2"
371
  ],
372
  [
373
  "i",
374
  "_24"
375
  ],
 
 
 
 
376
  [
377
  "i",
378
  "_11"
379
  ],
380
+ [
381
+ "o",
382
+ "ŋ"
383
+ ],
384
  [
385
  "e",
386
  "n"
387
  ],
388
  [
389
+ "i",
390
+ "_55 "
391
  ],
392
  [
393
+ "e",
394
  "_55 "
395
  ],
396
+ [
397
+ "u",
398
+ "ŋ"
399
+ ],
400
  [
401
  "i",
402
  "n"
 
406
  "_31"
407
  ],
408
  [
409
+ "t͡s",
410
+ "ʰ"
411
  ],
412
  [
413
+ "s",
414
+ "ɨ"
415
  ],
416
  [
417
+ "",
418
+ "ɕ"
419
  ],
420
  [
421
+ "o",
422
+ "_55"
423
  ],
424
  [
425
+ "k",
426
  "ʰ"
427
  ],
428
  [
429
+ "k",
430
+ "e_55 "
431
  ],
432
  [
433
  "a",
434
+ "n"
435
  ],
436
  [
437
  "u",
 
441
  "k",
442
  "_2"
443
  ],
 
 
 
 
444
  [
445
  "a",
446
+ "ŋ"
447
  ],
448
  [
449
+ "t͡ɕ",
450
  "ʰ"
451
  ],
452
  [
453
  "a",
454
+ "_55"
455
  ],
456
  [
457
+ "t_2",
458
+ " "
459
  ],
460
  [
461
+ "a",
462
+ "_24"
463
  ],
464
  [
465
+ "u",
466
+ "n"
467
+ ],
468
+ [
469
+ "_5",
470
+ " "
471
  ],
472
  [
473
  "o",
 
479
  ],
480
  [
481
  "u",
482
+ "_55 "
483
  ],
484
  [
485
+ "a",
486
+ "m"
487
  ],
488
  [
489
+ "u",
490
+ "_24 "
491
  ],
492
  [
493
  "e",
494
+ "_55"
495
  ],
496
  [
497
+ "p",
498
+ "ʰ"
499
  ],
500
  [
501
+ "o",
502
+ "n"
503
  ],
504
  [
505
+ "i",
506
+ "_11 "
507
  ],
508
  [
509
  "u",
510
  "_31"
511
  ],
512
  [
513
+ "t",
514
+ "o"
 
 
 
 
515
  ],
516
  [
517
  "o_55",
518
  "i_55 "
519
  ],
520
  [
521
+ "i_11",
522
+ "en"
523
  ],
524
  [
525
  "a",
526
+ "_31"
527
  ],
528
  [
529
+ "i",
530
+ "t_2"
531
+ ],
532
+ [
533
+ "i",
534
+ "_2"
535
+ ],
536
+ [
537
+ "e",
538
+ "_31"
539
+ ],
540
+ [
541
+ "i",
542
+ "_5"
543
+ ],
544
+ [
545
+ "uŋ",
546
+ "_24"
547
+ ],
548
+ [
549
+ "k_2",
550
+ " "
551
  ],
552
  [
553
  "ŋ",
554
  "in"
555
  ],
556
  [
557
+ "t͡s",
558
+ "ɨ"
559
  ],
560
  [
561
+ "i_55",
562
+ "en"
563
  ],
564
  [
565
+ "h",
566
+ "o"
567
  ],
568
  [
569
  "a",
570
  "_24 "
571
  ],
572
  [
573
+ "e",
574
+ "t_2 "
575
  ],
576
  [
577
+ "i",
578
+ "_24 "
579
  ],
580
  [
581
+ "t",
582
+ "_5"
583
  ],
584
  [
585
+ "k",
586
+ "o"
587
+ ],
588
+ [
589
+ "a",
590
+ "_11"
591
  ],
592
  [
593
  "e",
594
  "_24"
595
  ],
596
+ [
597
+ "u",
598
+ "_11"
599
+ ],
600
  [
601
  "e",
602
+ "t_2"
603
  ],
604
  [
605
+ "",
606
+ ""
607
  ],
608
  [
609
+ "a",
610
+ "p"
611
  ],
612
  [
613
+ "",
614
+ "_24"
615
  ],
616
  [
617
  "l",
618
  "o_11"
619
  ],
620
  [
621
+ "k",
622
+ "_5"
 
 
 
 
623
  ],
624
  [
625
+ "a_55",
626
+ "i_55"
627
  ],
628
  [
629
  "h",
630
  "e_55 "
631
  ],
632
  [
633
+ "i_24",
634
+ "u_24 "
 
 
 
 
635
  ],
636
  [
637
+ "",
638
+ "_31"
639
  ],
640
  [
641
+ "u",
642
+ "_31 "
643
  ],
644
  [
645
+ "t͡ɕʰ",
646
+ "i_55"
647
  ],
648
  [
649
+ "i_24",
650
+ "en"
651
  ],
652
  [
653
+ "t",
654
+ "_5 "
655
  ],
656
  [
657
+ "i",
658
+ "t_2 "
659
  ],
660
  [
661
+ "i_11en",
662
+ "_11 "
663
  ],
664
  [
665
+ "i",
666
+ "m"
667
  ],
668
  [
669
  "i",
670
+ "_31 "
671
  ],
672
  [
673
  "a",
674
  "_55 "
675
  ],
676
  [
677
+ "e",
678
+ "_31 "
679
  ],
680
  [
681
+ "̩",
682
+ "_11"
683
  ],
684
  [
685
+ "e",
686
+ "_11"
687
  ],
688
  [
689
+ "in",
 
 
 
 
 
 
 
 
690
  "_24"
691
  ],
692
  [
693
+ "m",
694
+ "̩_11"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
695
  ],
696
  [
697
+ "",
698
+ "p"
699
  ],
700
  [
701
  "oŋ",
702
  "_55 "
703
  ],
704
  [
705
+ "i_55en",
706
+ "_55"
 
 
 
 
 
 
 
 
707
  ],
708
  [
709
  "i_11en",
710
  "_11"
711
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
712
  [
713
  "v",
714
  "o_55i_55 "
715
  ],
716
  [
717
+ "k",
718
+ "_5 "
719
  ],
720
  [
721
+ "an",
722
+ "_11"
723
  ],
724
  [
725
+ "to",
726
  "_55 "
727
  ],
728
  [
729
+ "o",
730
+ "_24"
 
 
 
 
731
  ],
732
  [
733
  "t",
734
  "i_55 "
735
  ],
736
  [
737
+ "u",
738
+ "k_2"
 
 
 
 
 
 
 
 
739
  ],
740
  [
741
+ "k",
742
+ "i_24"
743
  ],
744
  [
745
+ "u",
746
+ "_11 "
747
  ],
748
  [
749
+ "k",
750
+ "e_55"
751
  ],
752
  [
753
  "oŋ",
754
+ "_55"
 
 
 
 
 
 
 
 
755
  ],
756
  [
757
+ "",
758
+ "_31 "
759
  ],
760
  [
761
  "oŋ",
762
  "_24 "
763
  ],
764
  [
765
+ "",
766
+ "_55"
767
  ],
768
  [
769
+ "o_55",
770
+ "i_55"
771
  ],
772
  [
773
  "a",
774
+ "k_2"
775
  ],
776
  [
777
+ "o",
778
+ "_31"
779
  ],
780
  [
781
+ "ŋin",
782
+ "_11"
783
  ],
784
  [
785
+ "lo_11",
786
+ "i_11 "
787
  ],
788
  [
789
+ "ŋin",
790
+ "_11 "
791
  ],
792
  [
793
+ "",
794
+ "a_55i_55"
795
  ],
796
  [
797
+ "",
798
+ "o_11"
799
  ],
800
  [
801
+ "",
802
+ "_24"
803
  ],
804
  [
805
+ "ŋ",
806
+ "i_5"
807
  ],
808
  [
809
+ "a",
810
+ "k_2 "
811
  ],
812
  [
813
  "i_31",
814
+ "a_31"
 
 
 
 
 
 
 
 
815
  ],
816
  [
817
+ "",
818
+ "_24 "
819
  ],
820
  [
821
+ "i_55",
822
+ ""
823
  ],
824
  [
825
+ "",
826
+ "n"
827
  ],
828
  [
829
+ "to",
830
+ "_31 "
831
  ],
832
  [
833
+ "t͡s",
834
+ "o_55"
835
  ],
836
  [
837
+ "t͡sʰ",
838
+ "ɨ"
839
  ],
840
  [
841
+ "ŋ",
842
+ "̩"
843
  ],
844
  [
845
+ "in",
846
+ "_11"
847
  ],
848
  [
849
+ "in",
850
  "_55"
851
  ],
852
  [
853
+ "i_55en",
854
+ "_55 "
855
  ],
856
  [
857
+ "ŋ",
858
+ "i_55"
859
  ],
860
  [
861
+ "",
862
+ "_11 "
863
  ],
864
  [
865
+ "sɨp",
866
+ "_5"
867
  ],
868
  [
869
+ "",
870
+ "_11"
871
  ],
872
  [
873
  "k",
874
+ "i_31"
 
 
 
 
 
 
 
 
875
  ],
876
  [
877
+ "i_24en",
878
  "_24"
879
  ],
880
  [
881
  "a",
882
+ "_31 "
 
 
 
 
883
  ],
884
  [
885
+ "",
886
+ "_11"
887
  ],
888
  [
889
+ "am",
890
+ "_24"
891
  ],
892
  [
893
+ "",
894
+ "e_11"
895
  ],
896
  [
897
+ "t",
898
+ "en"
899
  ],
900
  [
901
+ "t͡sʰ",
902
+ "u"
903
  ],
904
  [
905
+ "h",
906
+ "an_11"
907
  ],
908
  [
909
+ "p",
910
+ "un"
911
  ],
912
  [
913
+ "a",
914
+ "t_2"
915
  ],
916
  [
917
+ "a_55",
918
+ "i_55 "
919
  ],
920
  [
921
+ "k",
922
+ "i_11 "
923
  ],
924
  [
925
+ "u_55",
926
+ "i_55 "
927
  ],
928
  [
929
  "k",
930
+ "u"
931
  ],
932
  [
933
+ "i_31",
934
+ "oŋ_31"
935
  ],
936
  [
937
+ "e_24",
938
+ "u_24"
939
  ],
940
  [
941
+ "e_31",
942
+ "u_31"
943
  ],
944
  [
945
+ "an",
946
+ "_24"
947
  ],
948
  [
949
  "k",
950
  "a_24"
951
  ],
952
  [
953
+ "k",
954
+ "a_24 "
955
  ],
956
  [
957
+ "",
958
+ "i_11"
959
  ],
960
  [
961
  "an",
962
+ "_24 "
963
  ],
964
  [
965
+ "tʰo_11",
966
  "i_11"
967
  ],
968
  [
969
+ "m",
970
+ "o_11"
 
 
 
 
971
  ],
972
  [
973
+ "k",
974
+ "i_55"
975
  ],
976
  [
977
+ "ku",
978
+ "_2"
979
  ],
980
  [
981
+ "ko",
982
+ "_55 "
983
  ],
984
  [
985
+ "ŋ",
986
+ "a_11"
987
  ],
988
  [
989
+ "e_55",
990
+ "u_55"
991
  ],
992
  [
993
+ "t͡sɨ",
994
+ "n"
995
  ],
996
  [
997
+ "t͡s",
998
+ "o"
999
  ],
1000
  [
1001
+ "k",
1002
+ "in"
1003
  ],
1004
  [
1005
+ "im",
1006
  "_24"
1007
  ],
1008
  [
1009
+ "ŋ",
1010
+ "i_11en_11 "
1011
  ],
1012
  [
1013
+ "e_24",
1014
+ "u_24 "
1015
  ],
1016
  [
1017
+ "t",
1018
+ "et_2 "
1019
  ],
1020
  [
1021
+ "i_24en",
1022
+ "_24 "
1023
  ],
1024
  [
1025
+ "i",
1026
+ "p"
1027
  ],
1028
  [
1029
+ "on",
1030
+ "_24"
1031
  ],
1032
  [
1033
+ "un",
1034
+ "_11"
1035
  ],
1036
  [
1037
+ "k",
1038
+ "uŋ_24"
1039
  ],
1040
  [
1041
+ "s",
1042
+ "u_31"
1043
  ],
1044
  [
1045
+ "ap",
1046
+ "_2"
1047
  ],
1048
  [
1049
+ "",
1050
+ "_55 "
1051
  ],
1052
  [
1053
+ "",
1054
+ "_11 "
1055
  ],
1056
  [
1057
+ "on",
1058
+ "_55"
1059
  ],
1060
  [
1061
+ "",
1062
  "i_55"
1063
  ],
1064
  [
1065
+ "e",
1066
+ "t_5 "
1067
  ],
1068
  [
1069
  "tʰuŋ",
1070
  "_11 "
1071
  ],
1072
  [
1073
+ "an",
1074
+ "_55"
1075
  ],
1076
  [
1077
+ "o",
1078
+ "_11 "
1079
+ ],
1080
+ [
1081
+ "u",
1082
+ "k_2 "
1083
  ],
1084
  [
1085
  "t͡s",
1086
+ ""
1087
  ],
1088
  [
1089
+ "ho",
1090
+ "_31"
1091
  ],
1092
  [
1093
+ "i_2",
1094
+ "et_2"
1095
  ],
1096
  [
1097
+ "i_31",
1098
+ "en"
1099
  ],
1100
  [
1101
+ "k",
1102
+ "u_24"
1103
  ],
1104
  [
1105
+ "i_24",
1106
  "u_24"
1107
  ],
1108
  [
1109
  "aŋ",
1110
+ "_55"
1111
  ],
1112
  [
1113
+ "ŋ",
1114
+ "i_11"
1115
  ],
1116
  [
1117
+ "an",
1118
+ "_55 "
1119
  ],
1120
  [
1121
+ "an",
1122
+ "_31"
1123
+ ],
1124
+ [
1125
+ "h",
1126
+ "i_55 "
1127
  ]
1128
  ]
1129
  }