ms3c commited on
Commit
1ea32a8
·
1 Parent(s): 95edcf4

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 45,
3
+ "<s>": 44
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "42": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "43": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "44": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "45": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t": 0,
3
+ "\n": 1,
4
+ "0": 3,
5
+ "1": 4,
6
+ "2": 5,
7
+ "3": 6,
8
+ "4": 7,
9
+ "5": 8,
10
+ "6": 9,
11
+ "7": 10,
12
+ "8": 11,
13
+ "9": 12,
14
+ "[PAD]": 43,
15
+ "[UNK]": 42,
16
+ "_": 13,
17
+ "`": 14,
18
+ "a": 15,
19
+ "b": 16,
20
+ "c": 17,
21
+ "d": 18,
22
+ "e": 19,
23
+ "f": 20,
24
+ "g": 21,
25
+ "h": 22,
26
+ "i": 23,
27
+ "j": 24,
28
+ "k": 25,
29
+ "l": 26,
30
+ "m": 27,
31
+ "n": 28,
32
+ "o": 29,
33
+ "p": 30,
34
+ "q": 31,
35
+ "r": 32,
36
+ "s": 33,
37
+ "t": 34,
38
+ "u": 35,
39
+ "v": 36,
40
+ "w": 37,
41
+ "x": 38,
42
+ "y": 39,
43
+ "z": 40,
44
+ "|": 2,
45
+ "ū": 41
46
+ }