sanchit-gandhi HF staff commited on
Commit
fe560b3
1 Parent(s): 59dbe1e

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 +27 -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": "kno",
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 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 24,
3
+ "'": 22,
4
+ "a": 1,
5
+ "b": 8,
6
+ "c": 10,
7
+ "d": 14,
8
+ "e": 7,
9
+ "f": 20,
10
+ "g": 21,
11
+ "h": 11,
12
+ "i": 5,
13
+ "k": 12,
14
+ "m": 3,
15
+ "n": 2,
16
+ "o": 9,
17
+ "p": 23,
18
+ "s": 13,
19
+ "t": 15,
20
+ "u": 16,
21
+ "w": 18,
22
+ "y": 17,
23
+ "|": 0,
24
+ "ɔ": 6,
25
+ "ɛ": 4,
26
+ "‐": 19
27
+ }