Hugging Face's logo

Xenova
/
unispeech-sat-base-100h-libri-ft

Automatic Speech Recognition
Transformers.js
ONNX
unispeech-sat
Model card Files Community
Xenova HF staff commited on
Commit
674b53b
•
1 Parent(s): 4e5e37f

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +101 -0
tokenizer.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
11
+ "rstrip": true,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<s>",
18
+ "single_word": false,
19
+ "lstrip": true,
20
+ "rstrip": true,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
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
+ "<pad>": 0,
68
+ "<s>": 1,
69
+ "</s>": 2,
70
+ "<unk>": 3,
71
+ "|": 4,
72
+ "E": 5,
73
+ "T": 6,
74
+ "A": 7,
75
+ "O": 8,
76
+ "N": 9,
77
+ "I": 10,
78
+ "H": 11,
79
+ "S": 12,
80
+ "R": 13,
81
+ "D": 14,
82
+ "L": 15,
83
+ "U": 16,
84
+ "M": 17,
85
+ "W": 18,
86
+ "C": 19,
87
+ "F": 20,
88
+ "G": 21,
89
+ "Y": 22,
90
+ "P": 23,
91
+ "B": 24,
92
+ "V": 25,
93
+ "K": 26,
94
+ "'": 27,
95
+ "X": 28,
96
+ "J": 29,
97
+ "Q": 30,
98
+ "Z": 31
99
+ }
100
+ }
101
+ }