Hugging Face's logo

phonemetransformers
/
CHILDES-PortugueseBr-phoneme-tokenizer

Transformers
Inference Endpoints
Model card Files Community
CHILDES-PortugueseBr-phoneme-tokenizer
File size: 2,906 Bytes 
fbd5e1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cfa3f65
 
 
 
 
 
 
 
 
fbd5e1a
87fc94c
2b4611b
fbd5e1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87fc94c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fbd5e1a
 
 
 
 
 
87fc94c
 
26ee18d
 
 
 
 
 
 
 
 
 
 
 
 
1cd23db
26ee18d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fbd5e1a
 
 
 
 
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
156
157
158
159
160
161
162
163
164
165
166
167
168
 
{
  "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": "WORD_BOUNDARY",
      "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,
      "m": 4,
      "a": 5,
      "s̪": 6,
      "k": 7,
      "ɛ": 8,
      "ɾ": 9,
      "u": 10,
      "b": 11,
      "e": 12,
      "aʊ̯": 13,
      "ɡ": 14,
      "ɐ": 15,
      "oɪ̯": 16,
      "z": 17,
      "i": 18,
      "õ": 19,
      "t̪": 20,
      "eʊ̯": 21,
      "n̪": 22,
      "v": 23,
      "d̪": 24,
      "ɐ̃ʊ̯̃": 25,
      "eɪ̯": 26,
      "d̠ʒ": 27,
      "ẽɪ̯̃": 28,
      "p": 29,
      "r": 30,
      "ɔ": 31,
      "o": 32,
      "l": 33,
      "ɐ̃": 34,
      "ĩ": 35,
      "f": 36,
      "ɲ": 37,
      "ũ": 38,
      "uɪ̯": 39,
      "w": 40,
      "ʒ": 41,
      "iʊ̯": 42,
      "ʃ": 43,
      "oʊ̯": 44,
      "aɪ̯": 45,
      "ɔɪ̯": 46,
      "ɣ": 47,
      "ɛɪ̯": 48,
      "ɛʊ̯": 49,
      "ɪ̯": 50
    },
    "unk_token": "UNK"
  }
}