sanchit-gandhi HF staff commited on
Commit
e015410
1 Parent(s): 8c64566

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 +66 -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": "mon",
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 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 63,
3
+ "-": 62,
4
+ "a": 59,
5
+ "b": 39,
6
+ "c": 51,
7
+ "d": 52,
8
+ "e": 38,
9
+ "f": 43,
10
+ "g": 46,
11
+ "h": 61,
12
+ "i": 41,
13
+ "j": 36,
14
+ "k": 54,
15
+ "l": 37,
16
+ "m": 42,
17
+ "n": 44,
18
+ "o": 56,
19
+ "p": 40,
20
+ "q": 48,
21
+ "r": 47,
22
+ "s": 50,
23
+ "t": 60,
24
+ "u": 55,
25
+ "v": 49,
26
+ "w": 53,
27
+ "x": 45,
28
+ "y": 57,
29
+ "z": 58,
30
+ "|": 0,
31
+ "а": 1,
32
+ "б": 16,
33
+ "в": 20,
34
+ "г": 4,
35
+ "д": 6,
36
+ "е": 25,
37
+ "ж": 21,
38
+ "з": 23,
39
+ "и": 7,
40
+ "й": 12,
41
+ "к": 33,
42
+ "л": 10,
43
+ "м": 18,
44
+ "н": 3,
45
+ "о": 13,
46
+ "п": 32,
47
+ "р": 5,
48
+ "с": 15,
49
+ "т": 11,
50
+ "у": 14,
51
+ "ф": 34,
52
+ "х": 8,
53
+ "ц": 27,
54
+ "ч": 19,
55
+ "щ": 26,
56
+ "ъ": 35,
57
+ "ы": 24,
58
+ "ь": 22,
59
+ "э": 2,
60
+ "ю": 29,
61
+ "я": 28,
62
+ "ё": 31,
63
+ "ѳ": 17,
64
+ "ү": 9,
65
+ "—": 30
66
+ }