sanchit-gandhi HF staff commited on
Commit
84c3b7d
1 Parent(s): b29c577

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +4 -0
  2. tokenizer_config.json +12 -0
  3. vocab.json +81 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "|",
3
+ "unk_token": "<unk>"
4
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "is_uroman": false,
5
+ "language": "crk-script_syllabics",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "|",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 78,
3
+ "7": 77,
4
+ "9": 76,
5
+ "h": 63,
6
+ "t": 75,
7
+ "|": 0,
8
+ "ᐁ": 5,
9
+ "ᐃ": 3,
10
+ "ᐄ": 74,
11
+ "ᐅ": 19,
12
+ "ᐆ": 60,
13
+ "ᐊ": 4,
14
+ "ᐋ": 24,
15
+ "ᐟ": 26,
16
+ "ᐠ": 14,
17
+ "ᐢ": 11,
18
+ "ᐣ": 25,
19
+ "ᐤ": 23,
20
+ "ᐦ": 9,
21
+ "ᐧ": 1,
22
+ "ᐨ": 44,
23
+ "ᐩ": 56,
24
+ "ᐯ": 36,
25
+ "ᐱ": 30,
26
+ "ᐳ": 48,
27
+ "ᐴ": 72,
28
+ "ᐸ": 35,
29
+ "ᐹ": 55,
30
+ "ᑊ": 57,
31
+ "ᑌ": 32,
32
+ "ᑎ": 28,
33
+ "ᑐ": 33,
34
+ "ᑑ": 67,
35
+ "ᑕ": 8,
36
+ "ᑖ": 31,
37
+ "ᑦ": 49,
38
+ "ᑫ": 27,
39
+ "ᑭ": 2,
40
+ "ᑮ": 62,
41
+ "ᑯ": 17,
42
+ "ᑰ": 61,
43
+ "ᑲ": 7,
44
+ "ᑳ": 16,
45
+ "ᒉ": 52,
46
+ "ᒋ": 12,
47
+ "ᒌ": 73,
48
+ "ᒍ": 58,
49
+ "ᒐ": 59,
50
+ "ᒑ": 54,
51
+ "ᒣ": 43,
52
+ "ᒥ": 13,
53
+ "ᒦ": 71,
54
+ "ᒧ": 39,
55
+ "ᒨ": 65,
56
+ "ᒪ": 22,
57
+ "ᒫ": 20,
58
+ "ᒼ": 64,
59
+ "ᓀ": 45,
60
+ "ᓂ": 10,
61
+ "ᓃ": 68,
62
+ "ᓄ": 46,
63
+ "ᓅ": 69,
64
+ "ᓇ": 15,
65
+ "ᓈ": 37,
66
+ "ᓬ": 51,
67
+ "ᓭ": 42,
68
+ "ᓯ": 6,
69
+ "ᓰ": 70,
70
+ "ᓱ": 40,
71
+ "ᓲ": 66,
72
+ "ᓴ": 38,
73
+ "ᓵ": 50,
74
+ "ᔦ": 41,
75
+ "ᔨ": 18,
76
+ "ᔪ": 53,
77
+ "ᔭ": 21,
78
+ "ᔮ": 34,
79
+ "ᕒ": 47,
80
+ "ᕽ": 29
81
+ }