Gemmar commited on
Commit
8403279
1 Parent(s): 17e9e78

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 30,
3
+ "<s>": 29
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 28,
3
+ "[UNK]": 27,
4
+ "a": 1,
5
+ "b": 2,
6
+ "c": 3,
7
+ "d": 4,
8
+ "e": 5,
9
+ "f": 6,
10
+ "g": 7,
11
+ "h": 8,
12
+ "i": 9,
13
+ "j": 10,
14
+ "k": 11,
15
+ "l": 12,
16
+ "m": 13,
17
+ "n": 14,
18
+ "o": 15,
19
+ "p": 16,
20
+ "q": 17,
21
+ "r": 18,
22
+ "s": 19,
23
+ "t": 20,
24
+ "u": 21,
25
+ "v": 22,
26
+ "w": 23,
27
+ "x": 24,
28
+ "y": 25,
29
+ "z": 26,
30
+ "|": 0
31
+ }