sanchit-gandhi HF staff commited on
Commit
07999e5
1 Parent(s): e3a8836

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