Hugging Face's logo

phonemetransformers
/
CHILDES-Turkish-phoneme-tokenizer

Transformers
Inference Endpoints
Model card Files Community
CHILDES-Turkish-phoneme-tokenizer
File size: 2,598 Bytes 
933a330
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f7dd69
2f15a6a
aea0d32
1f7dd69
 
 
 
 
933a330
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2f15a6a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
933a330
 
 
 
 
 
2f15a6a
c82ed92
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
933a330
 
 
 
 
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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
 
{
  "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": 3,
      "content": "UTT_BOUNDARY",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Strip",
        "strip_left": true,
        "strip_right": true
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "UTT_BOUNDARY",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "UTT_BOUNDARY",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "UTT_BOUNDARY",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "UTT_BOUNDARY": {
        "id": "UTT_BOUNDARY",
        "ids": [
          3
        ],
        "tokens": [
          "UTT_BOUNDARY"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "UNK": 0,
      "PAD": 1,
      "WORD_BOUNDARY": 2,
      "UTT_BOUNDARY": 3,
      "s": 4,
      "æ": 5,
      "n": 6,
      "o": 7,
      "j": 8,
      "ʊ": 9,
      "ɔ": 10,
      "a": 11,
      "r": 12,
      "m": 13,
      "ɯ": 14,
      "k": 15,
      "ɪ": 16,
      "l": 17,
      "i": 18,
      "ɛ": 19,
      "v": 20,
      "d": 21,
      "d̠ʒ": 22,
      "y": 23,
      "t": 24,
      "b": 25,
      "u": 26,
      "z": 27,
      "ʃ": 28,
      "ɟ": 29,
      "e": 30,
      "p": 31,
      "ɡ": 32,
      "ɫ": 33,
      "h": 34,
      "t̠ʃ": 35,
      "ɾ": 36,
      "f": 37,
      "ø": 38,
      "œ": 39,
      "aː": 40,
      "c": 41,
      "ʊː": 42,
      "tː": 43,
      "oː": 44,
      "œː": 45,
      "ʒ": 46
    },
    "unk_token": "UNK"
  }
}