sanchit-gandhi commited on
Commit
6c8e209
·
1 Parent(s): 633803b

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 +34 -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": "heb",
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 31,
3
+ "'": 29,
4
+ "-": 30,
5
+ "|": 0,
6
+ "א": 3,
7
+ "ב": 8,
8
+ "ג": 20,
9
+ "ד": 15,
10
+ "ה": 4,
11
+ "ו": 1,
12
+ "ז": 23,
13
+ "ח": 16,
14
+ "ט": 25,
15
+ "י": 2,
16
+ "ך": 24,
17
+ "כ": 13,
18
+ "ל": 5,
19
+ "ם": 9,
20
+ "מ": 11,
21
+ "ן": 18,
22
+ "נ": 12,
23
+ "ס": 21,
24
+ "ע": 14,
25
+ "ף": 26,
26
+ "פ": 19,
27
+ "ץ": 27,
28
+ "צ": 22,
29
+ "ק": 17,
30
+ "ר": 10,
31
+ "ש": 7,
32
+ "ת": 6,
33
+ "—": 28
34
+ }