sanchit-gandhi HF staff commited on
Commit
60cf817
1 Parent(s): 8d84288

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 +39 -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": "mpp",
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 20,
3
+ "'": 25,
4
+ "-": 31,
5
+ "0": 32,
6
+ "1": 29,
7
+ "2": 19,
8
+ "3": 3,
9
+ "4": 6,
10
+ "5": 21,
11
+ "6": 24,
12
+ "7": 15,
13
+ "8": 35,
14
+ "9": 11,
15
+ "_": 0,
16
+ "a": 18,
17
+ "b": 17,
18
+ "c": 7,
19
+ "d": 9,
20
+ "e": 27,
21
+ "f": 22,
22
+ "g": 2,
23
+ "h": 28,
24
+ "i": 5,
25
+ "k": 26,
26
+ "l": 4,
27
+ "m": 30,
28
+ "n": 16,
29
+ "o": 1,
30
+ "p": 10,
31
+ "r": 33,
32
+ "s": 34,
33
+ "t": 8,
34
+ "u": 12,
35
+ "w": 23,
36
+ "y": 36,
37
+ "z": 14,
38
+ "­": 13
39
+ }