Hugging Face's logo

Felguk
/
Felguk-suno-or-people

Zero-Shot Classification
Transformers
wav2vec2
audio-classification
Suno
Inference Endpoints
Model card Files Community
Felguk commited on
Commit
34efe07
·
verified ·
1 Parent(s): 73d2fd5

Create tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +141 -0
tokenizer.json ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[SEP]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": {
53
+ "type": "Sequence",
54
+ "normalizers": [
55
+ {
56
+ "type": "NFC"
57
+ },
58
+ {
59
+ "type": "Lowercase"
60
+ }
61
+ ]
62
+ },
63
+ "pre_tokenizer": {
64
+ "type": "Whitespace"
65
+ },
66
+ "post_processor": {
67
+ "type": "TemplateProcessing",
68
+ "single": [
69
+ {
70
+ "SpecialToken",
71
+ "id": "[CLS]"
72
+ },
73
+ {
74
+ "Sequence",
75
+ "id": "A"
76
+ },
77
+ {
78
+ "SpecialToken",
79
+ "id": "[SEP]"
80
+ }
81
+ ],
82
+ "pair": [
83
+ {
84
+ "SpecialToken",
85
+ "id": "[CLS]"
86
+ },
87
+ {
88
+ "Sequence",
89
+ "id": "A"
90
+ },
91
+ {
92
+ "SpecialToken",
93
+ "id": "[SEP]"
94
+ },
95
+ {
96
+ "Sequence",
97
+ "id": "B"
98
+ },
99
+ {
100
+ "SpecialToken",
101
+ "id": "[SEP]"
102
+ }
103
+ ],
104
+ "special_tokens": {
105
+ "[CLS]": {
106
+ "id": "[CLS]",
107
+ "ids": [2]
108
+ },
109
+ "[SEP]": {
110
+ "id": "[SEP]",
111
+ "ids": [3]
112
+ }
113
+ }
114
+ },
115
+ "decoder": {
116
+ "type": "WordPiece",
117
+ "prefix": "##",
118
+ "cleanup": true
119
+ },
120
+ "model": {
121
+ "type": "WordPiece",
122
+ "unk_token": "[UNK]",
123
+ "continuing_subword_prefix": "##",
124
+ "max_input_chars_per_word": 100,
125
+ "vocab": {
126
+ "[PAD]": 0,
127
+ "[UNK]": 1,
128
+ "[CLS]": 2,
129
+ "[SEP]": 3,
130
+ "[MASK]": 4,
131
+ "the": 5,
132
+ "quick": 6,
133
+ "brown": 7,
134
+ "fox": 8,
135
+ "jumps": 9,
136
+ "over": 10,
137
+ "lazy": 11,
138
+ "dog": 12
139
+ }
140
+ }
141
+ }