ujs commited on
Commit
4c30b68
·
1 Parent(s): 93e8b45

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 31,
3
+ "<s>": 30
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
+ "model_max_length": 1000000000000000019884624838656,
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 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 0,
3
+ "+": 1,
4
+ "[PAD]": 29,
5
+ "[UNK]": 28,
6
+ "a": 2,
7
+ "b": 3,
8
+ "c": 4,
9
+ "d": 5,
10
+ "e": 6,
11
+ "f": 7,
12
+ "g": 8,
13
+ "h": 9,
14
+ "i": 10,
15
+ "j": 11,
16
+ "k": 12,
17
+ "l": 13,
18
+ "m": 14,
19
+ "n": 15,
20
+ "o": 16,
21
+ "p": 17,
22
+ "q": 18,
23
+ "r": 19,
24
+ "s": 20,
25
+ "t": 21,
26
+ "u": 22,
27
+ "v": 23,
28
+ "w": 24,
29
+ "x": 25,
30
+ "y": 26,
31
+ "z": 27
32
+ }