Samuael commited on
Commit
b15bbf9
β€’
1 Parent(s): 73a15cf

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 42,
3
+ "<s>": 41
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
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "39": {
12
+ "content": "[UNK]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "41": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "42": {
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 40,
3
+ "[PAD]": 0,
4
+ "[UNK]": 39,
5
+ "|": 29,
6
+ "αˆ…": 3,
7
+ "ል": 19,
8
+ "ም": 30,
9
+ "ር": 18,
10
+ "ሡ": 17,
11
+ "ሽ": 37,
12
+ "α‰…": 36,
13
+ "α‰₯": 28,
14
+ "α‰­": 10,
15
+ "ቡ": 23,
16
+ "ች": 32,
17
+ "αŠ•": 24,
18
+ "ኝ": 4,
19
+ "አ": 33,
20
+ "ኑ": 12,
21
+ "ኒ": 35,
22
+ "ኣ": 9,
23
+ "ኀ": 20,
24
+ "αŠ₯": 22,
25
+ "ኦ": 5,
26
+ "ኧ": 11,
27
+ "ክ": 16,
28
+ "ኰ": 26,
29
+ "ኸ": 8,
30
+ "ው": 6,
31
+ "ዝ": 15,
32
+ "α‹₯": 2,
33
+ "α‹­": 34,
34
+ "α‹΅": 21,
35
+ "αŒ…": 13,
36
+ "ግ": 14,
37
+ "αŒ₯": 7,
38
+ "ጭ": 31,
39
+ "ጡ": 27,
40
+ "ጽ": 25,
41
+ "ፍ": 38,
42
+ "ፕ": 1
43
+ }