kunhanw commited on
Commit
00ddc2e
1 Parent(s): 59dbf79

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 47,
3
+ "<s>": 46
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
+ "44": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "45": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "46": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "47": {
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": "grn",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "grn": {
3
+ "[PAD]": 45,
4
+ "[UNK]": 44,
5
+ "a": 1,
6
+ "b": 2,
7
+ "c": 3,
8
+ "d": 4,
9
+ "e": 5,
10
+ "f": 6,
11
+ "g": 7,
12
+ "h": 8,
13
+ "i": 9,
14
+ "j": 10,
15
+ "k": 11,
16
+ "l": 12,
17
+ "m": 13,
18
+ "n": 14,
19
+ "o": 15,
20
+ "p": 16,
21
+ "q": 17,
22
+ "r": 18,
23
+ "s": 19,
24
+ "t": 20,
25
+ "u": 21,
26
+ "v": 22,
27
+ "x": 23,
28
+ "y": 24,
29
+ "z": 25,
30
+ "|": 0,
31
+ "¡": 26,
32
+ "á": 27,
33
+ "ã": 28,
34
+ "é": 29,
35
+ "í": 30,
36
+ "ñ": 31,
37
+ "ó": 32,
38
+ "õ": 33,
39
+ "ú": 34,
40
+ "ý": 35,
41
+ "ĩ": 36,
42
+ "ũ": 37,
43
+ "ʼ": 38,
44
+ "̃": 39,
45
+ "ḡ": 40,
46
+ "ẽ": 41,
47
+ "ỹ": 42,
48
+ "’": 43
49
+ }
50
+ }