linlinlin commited on
Commit
964806e
·
1 Parent(s): dd3acf3

Upload tokenizer

Browse files
Files changed (1) hide show
  1. vocab.json +114 -114
vocab.json CHANGED
@@ -1,118 +1,118 @@
1
  {
2
- "aɪ": 98,
3
- "aɪə": 109,
4
- "aɪɚ": 23,
5
- "aʊ": 104,
6
- "b": 8,
7
- "d": 93,
8
- "dʒ": 56,
9
- "eɪ": 44,
10
- "f": 58,
11
- "h": 67,
12
- "i": 88,
13
- "iə": 81,
14
- "iː": 100,
15
- "j": 115,
16
- "k": 68,
17
- "l": 36,
18
- "m": 51,
19
- "n": 55,
20
- "n̩": 7,
21
- "oʊ": 40,
22
- "oː": 103,
23
- "oːɹ": 9,
24
- "p": 21,
25
- "r": 72,
26
- "s": 24,
27
- "t": 77,
28
- "tʃ": 114,
29
- "uː": 57,
30
- "v": 41,
31
- "w": 107,
32
- "x": 73,
33
- "z": 14,
34
  "|": 0,
35
- "æ": 62,
36
- "ð": 32,
37
- "ŋ": 89,
38
- "ɐ": 61,
39
- "ɑː": 85,
40
- "ɑːɹ": 84,
41
- "ɔ": 108,
42
- "ɔɪ": 97,
43
- "ɔː": 17,
44
- "ɔːɹ": 26,
45
- "ə": 18,
46
- "əl": 35,
47
- "ɚ": 10,
48
- "ɛ": 86,
49
- "ɛɹ": 78,
50
- "ɜː": 6,
51
- "ɡ": 42,
52
- "ɪ": 87,
53
- "ɪɹ": 82,
54
- "ɹ": 20,
55
- "ɾ": 59,
56
- "ʃ": 33,
57
- "ʊ": 54,
58
- "ʊɹ": 94,
59
- "ʌ": 74,
60
- "ʒ": 112,
61
  "ʔ": 66,
62
- "ˈaɪ": 52,
63
- "ˈaɪə": 16,
64
- "ˈaɪɚ": 101,
65
- "ˈaʊ": 13,
66
- "ˈeɪ": 64,
67
- "ˈiə": 83,
68
- "ˈiː": 48,
69
- "ˈoʊ": 49,
70
- "ˈoː": 34,
71
- "ˈoːɹ": 90,
72
- "ˈuː": 69,
73
- "ˈæ": 19,
74
- "ˈɑː": 47,
75
- "ˈɑːɹ": 102,
76
- "ˈɔ": 50,
77
- "ˈɔɪ": 43,
78
- "ˈɔː": 37,
79
- "ˈɔːɹ": 105,
80
- "ˈɚ": 5,
81
- "ˈɛ": 76,
82
- "ˈɛɹ": 80,
83
- "ˈɜː": 30,
84
- "ˈɪ": 31,
85
- "ˈɪɹ": 39,
86
- "ˈʊ": 22,
87
- "ˈʊɹ": 15,
88
- "ˈʌ": 113,
89
- "ˌaɪ": 95,
90
- "ˌaɪɚ": 29,
91
- "ˌaʊ": 2,
92
- "ˌeɪ": 79,
93
- "ˌiə": 11,
94
- "ˌiː": 25,
95
- "ˌn̩": 45,
96
- "ˌoʊ": 70,
97
- "ˌoː": 28,
98
- "ˌoːɹ": 110,
99
- "ˌuː": 75,
100
- "ˌæ": 106,
101
- "ˌɐ": 12,
102
- "ˌɑː": 96,
103
- "ˌɑːɹ": 111,
104
- "ˌɔ": 38,
105
- "ˌɔɪ": 92,
106
- "ˌɔː": 4,
107
- "ˌɔːɹ": 46,
108
- "ˌɛ": 65,
109
- "ˌɛɹ": 71,
110
- "ˌɜː": 99,
111
- "ˌɪ": 91,
112
- "ˌɪɹ": 27,
113
- "ˌʊ": 60,
114
- "ˌʊɹ": 3,
115
- "ˌʌ": 1,
116
- "θ": 63,
117
- "ᵻ": 53
118
  }
 
1
  {
2
+ "aɪ": 16,
3
+ "aɪə": 70,
4
+ "aɪɚ": 60,
5
+ "aʊ": 33,
6
+ "b": 93,
7
+ "d": 34,
8
+ "dʒ": 43,
9
+ "eɪ": 46,
10
+ "f": 112,
11
+ "h": 92,
12
+ "i": 97,
13
+ "iə": 2,
14
+ "iː": 27,
15
+ "j": 88,
16
+ "k": 32,
17
+ "l": 74,
18
+ "m": 99,
19
+ "n": 7,
20
+ "n̩": 25,
21
+ "oʊ": 20,
22
+ "oː": 9,
23
+ "oːɹ": 94,
24
+ "p": 73,
25
+ "r": 18,
26
+ "s": 55,
27
+ "t": 51,
28
+ "tʃ": 96,
29
+ "uː": 52,
30
+ "v": 19,
31
+ "w": 76,
32
+ "x": 71,
33
+ "z": 21,
34
  "|": 0,
35
+ "æ": 26,
36
+ "ð": 79,
37
+ "ŋ": 61,
38
+ "ɐ": 104,
39
+ "ɑː": 103,
40
+ "ɑːɹ": 31,
41
+ "ɔ": 114,
42
+ "ɔɪ": 24,
43
+ "ɔː": 8,
44
+ "ɔːɹ": 44,
45
+ "ə": 35,
46
+ "əl": 90,
47
+ "ɚ": 110,
48
+ "ɛ": 82,
49
+ "ɛɹ": 29,
50
+ "ɜː": 65,
51
+ "ɡ": 6,
52
+ "ɪ": 14,
53
+ "ɪɹ": 62,
54
+ "ɹ": 83,
55
+ "ɾ": 11,
56
+ "ʃ": 4,
57
+ "ʊ": 15,
58
+ "ʊɹ": 78,
59
+ "ʌ": 1,
60
+ "ʒ": 91,
61
  "ʔ": 66,
62
+ "ˈaɪ": 45,
63
+ "ˈaɪə": 22,
64
+ "ˈaɪɚ": 40,
65
+ "ˈaʊ": 86,
66
+ "ˈeɪ": 53,
67
+ "ˈiə": 77,
68
+ "ˈiː": 3,
69
+ "ˈoʊ": 85,
70
+ "ˈoː": 109,
71
+ "ˈoːɹ": 13,
72
+ "ˈuː": 115,
73
+ "ˈæ": 57,
74
+ "ˈɑː": 102,
75
+ "ˈɑːɹ": 87,
76
+ "ˈɔ": 41,
77
+ "ˈɔɪ": 38,
78
+ "ˈɔː": 36,
79
+ "ˈɔːɹ": 68,
80
+ "ˈɚ": 64,
81
+ "ˈɛ": 72,
82
+ "ˈɛɹ": 63,
83
+ "ˈɜː": 37,
84
+ "ˈɪ": 59,
85
+ "ˈɪɹ": 108,
86
+ "ˈʊ": 80,
87
+ "ˈʊɹ": 17,
88
+ "ˈʌ": 42,
89
+ "ˌaɪ": 56,
90
+ "ˌaɪɚ": 50,
91
+ "ˌaʊ": 23,
92
+ "ˌeɪ": 47,
93
+ "ˌiə": 12,
94
+ "ˌiː": 98,
95
+ "ˌn̩": 10,
96
+ "ˌoʊ": 54,
97
+ "ˌoː": 67,
98
+ "ˌoːɹ": 30,
99
+ "ˌuː": 39,
100
+ "ˌæ": 58,
101
+ "ˌɐ": 48,
102
+ "ˌɑː": 28,
103
+ "ˌɑːɹ": 113,
104
+ "ˌɔ": 95,
105
+ "ˌɔɪ": 100,
106
+ "ˌɔː": 75,
107
+ "ˌɔːɹ": 111,
108
+ "ˌɛ": 101,
109
+ "ˌɛɹ": 106,
110
+ "ˌɜː": 84,
111
+ "ˌɪ": 5,
112
+ "ˌɪɹ": 81,
113
+ "ˌʊ": 49,
114
+ "ˌʊɹ": 105,
115
+ "ˌʌ": 69,
116
+ "θ": 89,
117
+ "ᵻ": 107
118
  }