sanchit-gandhi HF staff commited on
Commit
e7adec0
1 Parent(s): 8afd676

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