skipperjo commited on
Commit
390446c
1 Parent(s): 0a31075

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 50,
3
+ "<s>": 49
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 48,
3
+ "[UNK]": 47,
4
+ "`": 1,
5
+ "a": 2,
6
+ "b": 3,
7
+ "c": 4,
8
+ "d": 5,
9
+ "e": 6,
10
+ "f": 7,
11
+ "g": 8,
12
+ "h": 9,
13
+ "i": 10,
14
+ "j": 11,
15
+ "k": 12,
16
+ "l": 13,
17
+ "m": 14,
18
+ "n": 15,
19
+ "o": 16,
20
+ "p": 17,
21
+ "q": 18,
22
+ "r": 19,
23
+ "s": 20,
24
+ "t": 21,
25
+ "u": 22,
26
+ "v": 23,
27
+ "w": 24,
28
+ "x": 25,
29
+ "y": 26,
30
+ "z": 27,
31
+ "|": 0,
32
+ "á": 28,
33
+ "ä": 29,
34
+ "é": 30,
35
+ "í": 31,
36
+ "ó": 32,
37
+ "ô": 33,
38
+ "ö": 34,
39
+ "ú": 35,
40
+ "ý": 36,
41
+ "č": 37,
42
+ "ď": 38,
43
+ "ĺ": 39,
44
+ "ľ": 40,
45
+ "ň": 41,
46
+ "ŕ": 42,
47
+ "š": 43,
48
+ "ť": 44,
49
+ "ž": 45,
50
+ "̌": 46
51
+ }