sanchit-gandhi HF staff commited on
Commit
cfa66e8
·
1 Parent(s): d079bc3

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 +33 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "6",
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": "twb",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "6",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 7,
3
+ "'": 13,
4
+ "-": 8,
5
+ "0": 25,
6
+ "1": 18,
7
+ "2": 6,
8
+ "3": 4,
9
+ "4": 22,
10
+ "6": 0,
11
+ "7": 26,
12
+ "_": 15,
13
+ "a": 19,
14
+ "b": 10,
15
+ "d": 3,
16
+ "e": 12,
17
+ "f": 24,
18
+ "g": 16,
19
+ "i": 1,
20
+ "k": 20,
21
+ "l": 27,
22
+ "m": 29,
23
+ "n": 30,
24
+ "o": 2,
25
+ "p": 21,
26
+ "r": 9,
27
+ "s": 14,
28
+ "t": 23,
29
+ "u": 5,
30
+ "v": 28,
31
+ "w": 17,
32
+ "y": 11
33
+ }