jlvdoorn commited on
Commit
f860cc6
1 Parent(s): a6d63bd

Upload 4 files

Browse files
Files changed (4) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +133 -0
  3. tokenizer.json +0 -0
  4. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|startoftranscript|>",
4
+ "<|en|>",
5
+ "<|zh|>",
6
+ "<|de|>",
7
+ "<|es|>",
8
+ "<|ru|>",
9
+ "<|ko|>",
10
+ "<|fr|>",
11
+ "<|ja|>",
12
+ "<|pt|>",
13
+ "<|tr|>",
14
+ "<|pl|>",
15
+ "<|ca|>",
16
+ "<|nl|>",
17
+ "<|ar|>",
18
+ "<|sv|>",
19
+ "<|it|>",
20
+ "<|id|>",
21
+ "<|hi|>",
22
+ "<|fi|>",
23
+ "<|vi|>",
24
+ "<|he|>",
25
+ "<|uk|>",
26
+ "<|el|>",
27
+ "<|ms|>",
28
+ "<|cs|>",
29
+ "<|ro|>",
30
+ "<|da|>",
31
+ "<|hu|>",
32
+ "<|ta|>",
33
+ "<|no|>",
34
+ "<|th|>",
35
+ "<|ur|>",
36
+ "<|hr|>",
37
+ "<|bg|>",
38
+ "<|lt|>",
39
+ "<|la|>",
40
+ "<|mi|>",
41
+ "<|ml|>",
42
+ "<|cy|>",
43
+ "<|sk|>",
44
+ "<|te|>",
45
+ "<|fa|>",
46
+ "<|lv|>",
47
+ "<|bn|>",
48
+ "<|sr|>",
49
+ "<|az|>",
50
+ "<|sl|>",
51
+ "<|kn|>",
52
+ "<|et|>",
53
+ "<|mk|>",
54
+ "<|br|>",
55
+ "<|eu|>",
56
+ "<|is|>",
57
+ "<|hy|>",
58
+ "<|ne|>",
59
+ "<|mn|>",
60
+ "<|bs|>",
61
+ "<|kk|>",
62
+ "<|sq|>",
63
+ "<|sw|>",
64
+ "<|gl|>",
65
+ "<|mr|>",
66
+ "<|pa|>",
67
+ "<|si|>",
68
+ "<|km|>",
69
+ "<|sn|>",
70
+ "<|yo|>",
71
+ "<|so|>",
72
+ "<|af|>",
73
+ "<|oc|>",
74
+ "<|ka|>",
75
+ "<|be|>",
76
+ "<|tg|>",
77
+ "<|sd|>",
78
+ "<|gu|>",
79
+ "<|am|>",
80
+ "<|yi|>",
81
+ "<|lo|>",
82
+ "<|uz|>",
83
+ "<|fo|>",
84
+ "<|ht|>",
85
+ "<|ps|>",
86
+ "<|tk|>",
87
+ "<|nn|>",
88
+ "<|mt|>",
89
+ "<|sa|>",
90
+ "<|lb|>",
91
+ "<|my|>",
92
+ "<|bo|>",
93
+ "<|tl|>",
94
+ "<|mg|>",
95
+ "<|as|>",
96
+ "<|tt|>",
97
+ "<|haw|>",
98
+ "<|ln|>",
99
+ "<|ha|>",
100
+ "<|ba|>",
101
+ "<|jw|>",
102
+ "<|su|>",
103
+ "<|yue|>",
104
+ "<|translate|>",
105
+ "<|transcribe|>",
106
+ "<|startoflm|>",
107
+ "<|startofprev|>",
108
+ "<|nospeech|>",
109
+ "<|notimestamps|>"
110
+ ],
111
+ "bos_token": {
112
+ "content": "<|endoftext|>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<|endoftext|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": "<|endoftext|>",
126
+ "unk_token": {
127
+ "content": "<|endoftext|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false
132
+ }
133
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff