hippopotam commited on
Commit
4c5b155
1 Parent(s): 2e139e8

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 43,
3
+ "<s>": 42
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
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "./",
6
+ "pad_token": "[PAD]",
7
+ "replace_word_delimiter_char": " ",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 0,
3
+ "(": 1,
4
+ ")": 2,
5
+ "[PAD]": 41,
6
+ "[UNK]": 40,
7
+ "a": 3,
8
+ "b": 4,
9
+ "c": 5,
10
+ "d": 6,
11
+ "e": 7,
12
+ "f": 8,
13
+ "g": 9,
14
+ "h": 10,
15
+ "i": 11,
16
+ "j": 12,
17
+ "k": 13,
18
+ "l": 14,
19
+ "m": 15,
20
+ "n": 16,
21
+ "o": 17,
22
+ "p": 18,
23
+ "q": 19,
24
+ "r": 20,
25
+ "s": 21,
26
+ "t": 22,
27
+ "u": 23,
28
+ "v": 24,
29
+ "w": 25,
30
+ "x": 26,
31
+ "y": 27,
32
+ "z": 28,
33
+ "ç": 29,
34
+ "é": 30,
35
+ "ë": 31,
36
+ "ö": 32,
37
+ "ü": 33,
38
+ "ğ": 34,
39
+ "ı": 35,
40
+ "ş": 36,
41
+ "̇": 37,
42
+ "’": 38,
43
+ "…": 39
44
+ }