sanchit-gandhi commited on
Commit
a549ee2
·
1 Parent(s): c086b00

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": "mam-dialect_southern",
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
+ "'": 1,
4
+ "-": 25,
5
+ "a": 3,
6
+ "b": 15,
7
+ "c": 20,
8
+ "d": 23,
9
+ "e": 5,
10
+ "g": 28,
11
+ "h": 21,
12
+ "i": 6,
13
+ "j": 7,
14
+ "k": 9,
15
+ "l": 10,
16
+ "m": 16,
17
+ "n": 4,
18
+ "o": 13,
19
+ "p": 22,
20
+ "q": 14,
21
+ "r": 24,
22
+ "s": 18,
23
+ "t": 2,
24
+ "u": 8,
25
+ "w": 19,
26
+ "x": 11,
27
+ "y": 12,
28
+ "z": 17,
29
+ "|": 0,
30
+ "ú": 29,
31
+ "́": 30,
32
+ "ẍ": 27,
33
+ "—": 26
34
+ }