sanchit-gandhi HF staff commited on
Commit
d4d4016
1 Parent(s): e39e77f

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 +30 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "c",
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": true,
5
+ "language": "amh",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "c",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 12,
3
+ "'": 14,
4
+ "_": 1,
5
+ "a": 21,
6
+ "b": 19,
7
+ "c": 0,
8
+ "d": 26,
9
+ "e": 5,
10
+ "f": 3,
11
+ "g": 27,
12
+ "h": 9,
13
+ "i": 24,
14
+ "j": 7,
15
+ "k": 22,
16
+ "l": 2,
17
+ "m": 6,
18
+ "n": 16,
19
+ "o": 10,
20
+ "p": 4,
21
+ "q": 18,
22
+ "r": 8,
23
+ "s": 13,
24
+ "t": 15,
25
+ "u": 17,
26
+ "w": 20,
27
+ "x": 23,
28
+ "y": 25,
29
+ "z": 11
30
+ }