Hugging Face's logo

phonemetransformers
/
CHILDES-Icelandic-phoneme-tokenizer

Transformers
Inference Endpoints
Model card Files Community
CHILDES-Icelandic-phoneme-tokenizer
File size: 2,342 Bytes 
9777402
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cf78632
 
 
 
 
 
 
 
 
9777402
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
 
{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "UNK",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "PAD",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "BOS",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "EOS",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 54,
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Replace",
        "pattern": {
          "String": "\n"
        },
        "content": " UTT_BOUNDARY"
      },
      {
        "type": "Strip",
        "strip_left": true,
        "strip_right": true
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "UNK": 0,
      "PAD": 1,
      "BOS": 2,
      "EOS": 3,
      "WORD_BOUNDARY": 4,
      "UTT_BOUNDARY": 5,
      "aː": 6,
      "ɾ": 7,
      "r": 8,
      "ɪ": 9,
      "ɛ": 10,
      "d": 11,
      "s": 12,
      "j": 13,
      "a": 14,
      "b": 15,
      "iː": 16,
      "k": 17,
      "ʋ": 18,
      "ɛː": 19,
      "θ": 20,
      "i": 21,
      "l": 22,
      "n": 23,
      "uː": 24,
      "ð": 25,
      "ɡ": 26,
      "ɔ": 27,
      "h": 28,
      "aʊ": 29,
      "y": 30,
      "m": 31,
      "f": 32,
      "ɔː": 33,
      "x": 34,
      "ɟ": 35,
      "t": 36,
      "eɪ": 37,
      "oʊ": 38,
      "p": 39,
      "ŋ": 40,
      "ɣ": 41,
      "yː": 42,
      "u": 43,
      "ɪː": 44,
      "œ": 45,
      "aɪ": 46,
      "ç": 47,
      "ə": 48,
      "øy": 49,
      "c": 50,
      "ɲ": 51,
      "œː": 52,
      "ɔɪ": 53
    },
    "unk_token": "UNK"
  }
}