Hugging Face's logo

Xenova
/
wav2vec2-bert-CV16-en

Automatic Speech Recognition
Transformers.js
ONNX
wav2vec2-bert
Model card Files Community
1
Xenova HF staff commited on
Commit
42e9268
•
1 Parent(s): 46caa73

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +102 -0
tokenizer.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 2,
8
+ "content": "</s>",
9
+ "single_word": false,
10
+ "lstrip": true,
11
+ "rstrip": true,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 0,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": true,
20
+ "rstrip": true,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 1,
26
+ "content": "<s>",
27
+ "single_word": false,
28
+ "lstrip": true,
29
+ "rstrip": true,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": true,
38
+ "rstrip": true,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": {
44
+ "type": "Replace",
45
+ "pattern": {
46
+ "String": " "
47
+ },
48
+ "content": "|"
49
+ },
50
+ "pre_tokenizer": {
51
+ "type": "Split",
52
+ "pattern": {
53
+ "Regex": ""
54
+ },
55
+ "behavior": "Isolated",
56
+ "invert": false
57
+ },
58
+ "post_processor": null,
59
+ "decoder": {
60
+ "type": "CTC",
61
+ "pad_token": "<pad>",
62
+ "word_delimiter_token": "|",
63
+ "cleanup": true
64
+ },
65
+ "model": {
66
+ "vocab": {
67
+ "'": 5,
68
+ "-": 6,
69
+ "</s>": 2,
70
+ "<pad>": 0,
71
+ "<s>": 1,
72
+ "<unk>": 3,
73
+ "a": 7,
74
+ "b": 8,
75
+ "c": 9,
76
+ "d": 10,
77
+ "e": 11,
78
+ "f": 12,
79
+ "g": 13,
80
+ "h": 14,
81
+ "i": 15,
82
+ "j": 16,
83
+ "k": 17,
84
+ "l": 18,
85
+ "m": 19,
86
+ "n": 20,
87
+ "o": 21,
88
+ "p": 22,
89
+ "q": 23,
90
+ "r": 24,
91
+ "s": 25,
92
+ "t": 26,
93
+ "u": 27,
94
+ "v": 28,
95
+ "w": 29,
96
+ "x": 30,
97
+ "y": 31,
98
+ "z": 32,
99
+ "|": 4
100
+ }
101
+ }
102
+ }