sanchit-gandhi HF staff commited on
Commit
b90cfdf
1 Parent(s): 6c6d274

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 +42 -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": "hif",
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 39,
3
+ "'": 30,
4
+ "-": 29,
5
+ "0": 33,
6
+ "1": 35,
7
+ "2": 38,
8
+ "4": 34,
9
+ "6": 36,
10
+ "a": 1,
11
+ "b": 13,
12
+ "c": 20,
13
+ "d": 18,
14
+ "e": 2,
15
+ "f": 25,
16
+ "g": 15,
17
+ "h": 3,
18
+ "i": 4,
19
+ "j": 17,
20
+ "k": 5,
21
+ "l": 12,
22
+ "m": 9,
23
+ "n": 10,
24
+ "o": 11,
25
+ "p": 16,
26
+ "q": 31,
27
+ "r": 6,
28
+ "s": 8,
29
+ "t": 14,
30
+ "u": 7,
31
+ "v": 28,
32
+ "w": 21,
33
+ "x": 32,
34
+ "y": 19,
35
+ "z": 27,
36
+ "|": 0,
37
+ "ñ": 22,
38
+ "ḍ": 26,
39
+ "ṛ": 24,
40
+ "ṭ": 23,
41
+ "–": 37
42
+ }