sanchit-gandhi commited on
Commit
9bc4712
·
1 Parent(s): f6695cc

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 +38 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ş",
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": "tuk-script_latin",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ş",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 32,
3
+ "'": 12,
4
+ "-": 24,
5
+ "_": 14,
6
+ "a": 8,
7
+ "b": 2,
8
+ "d": 19,
9
+ "e": 35,
10
+ "f": 20,
11
+ "g": 9,
12
+ "h": 11,
13
+ "i": 17,
14
+ "j": 25,
15
+ "k": 16,
16
+ "l": 34,
17
+ "m": 3,
18
+ "n": 29,
19
+ "o": 21,
20
+ "p": 33,
21
+ "r": 26,
22
+ "s": 7,
23
+ "t": 22,
24
+ "u": 15,
25
+ "w": 5,
26
+ "y": 4,
27
+ "z": 13,
28
+ "ä": 23,
29
+ "ç": 30,
30
+ "ö": 27,
31
+ "ü": 10,
32
+ "ý": 1,
33
+ "ň": 18,
34
+ "ş": 0,
35
+ "ž": 6,
36
+ "‐": 31,
37
+ "–": 28
38
+ }