lyimo commited on
Commit
e18b57d
1 Parent(s): 96ed9e4

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 58,
3
+ "<s>": 57
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "(": 1,
3
+ ")": 2,
4
+ "*": 3,
5
+ "/": 4,
6
+ "=": 5,
7
+ "[PAD]": 56,
8
+ "[UNK]": 55,
9
+ "_": 6,
10
+ "`": 7,
11
+ "a": 8,
12
+ "b": 9,
13
+ "c": 10,
14
+ "d": 11,
15
+ "e": 12,
16
+ "f": 13,
17
+ "g": 14,
18
+ "h": 15,
19
+ "i": 16,
20
+ "j": 17,
21
+ "k": 18,
22
+ "l": 19,
23
+ "m": 20,
24
+ "n": 21,
25
+ "o": 22,
26
+ "p": 23,
27
+ "q": 24,
28
+ "r": 25,
29
+ "s": 26,
30
+ "t": 27,
31
+ "u": 28,
32
+ "v": 29,
33
+ "w": 30,
34
+ "x": 31,
35
+ "y": 32,
36
+ "z": 33,
37
+ "|": 0,
38
+ "°": 34,
39
+ "µ": 35,
40
+ "á": 36,
41
+ "ã": 37,
42
+ "å": 38,
43
+ "é": 39,
44
+ "ë": 40,
45
+ "í": 41,
46
+ "ï": 42,
47
+ "ñ": 43,
48
+ "ó": 44,
49
+ "ö": 45,
50
+ "ø": 46,
51
+ "ú": 47,
52
+ "š": 48,
53
+ "ū": 49,
54
+ "ː": 50,
55
+ "ụ": 51,
56
+ "’": 52,
57
+ "•": 53,
58
+ "…": 54
59
+ }