sanchit-gandhi HF staff commited on
Commit
2e4d92c
1 Parent(s): da546ab

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 +27 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "m",
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": "mtd",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "m",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 20,
3
+ "-": 4,
4
+ "_": 3,
5
+ "a": 1,
6
+ "b": 2,
7
+ "c": 8,
8
+ "d": 16,
9
+ "e": 19,
10
+ "g": 12,
11
+ "h": 14,
12
+ "i": 9,
13
+ "j": 18,
14
+ "k": 23,
15
+ "l": 17,
16
+ "m": 0,
17
+ "n": 22,
18
+ "o": 10,
19
+ "p": 13,
20
+ "r": 6,
21
+ "s": 11,
22
+ "t": 5,
23
+ "u": 24,
24
+ "w": 21,
25
+ "y": 7,
26
+ "ꞌ": 15
27
+ }