sanchit-gandhi HF staff commited on
Commit
8f44fb4
1 Parent(s): 16809e4

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 +41 -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": "mam-dialect_western",
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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 38,
3
+ "'": 6,
4
+ "-": 24,
5
+ "a": 2,
6
+ "b": 15,
7
+ "c": 8,
8
+ "d": 21,
9
+ "e": 5,
10
+ "f": 35,
11
+ "g": 30,
12
+ "h": 23,
13
+ "i": 4,
14
+ "j": 7,
15
+ "k": 14,
16
+ "l": 9,
17
+ "m": 18,
18
+ "n": 3,
19
+ "o": 13,
20
+ "p": 20,
21
+ "q": 27,
22
+ "r": 22,
23
+ "s": 16,
24
+ "t": 1,
25
+ "u": 12,
26
+ "v": 36,
27
+ "w": 19,
28
+ "x": 10,
29
+ "y": 11,
30
+ "z": 17,
31
+ "|": 0,
32
+ "á": 32,
33
+ "é": 31,
34
+ "í": 29,
35
+ "ñ": 37,
36
+ "ó": 34,
37
+ "ú": 26,
38
+ "̈": 25,
39
+ "ẍ": 33,
40
+ "—": 28
41
+ }