Umong commited on
Commit
bea9c4a
1 Parent(s): 1620333

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 64,
3
+ "<s>": 63,
4
+ "[PAD]": 65
5
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "content": "[PAD]",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": "<s>",
26
+ "eos_token": "</s>",
27
+ "pad_token": "[PAD]",
28
+ "unk_token": "[UNK]"
29
+ }
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": "ben",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ben": {
3
+ "[PAD]": 64,
4
+ "[UNK]": 64,
5
+ "|": 0,
6
+ "ঁ": 1,
7
+ "ং": 2,
8
+ "ঃ": 3,
9
+ "অ": 4,
10
+ "আ": 5,
11
+ "ই": 6,
12
+ "ঈ": 7,
13
+ "উ": 8,
14
+ "ঊ": 9,
15
+ "ঋ": 10,
16
+ "এ": 11,
17
+ "ঐ": 12,
18
+ "ও": 13,
19
+ "ঔ": 14,
20
+ "ক": 15,
21
+ "খ": 16,
22
+ "গ": 17,
23
+ "ঘ": 18,
24
+ "ঙ": 19,
25
+ "চ": 20,
26
+ "ছ": 21,
27
+ "জ": 22,
28
+ "ঝ": 23,
29
+ "ঞ": 24,
30
+ "ট": 25,
31
+ "ঠ": 26,
32
+ "ড": 27,
33
+ "ঢ": 28,
34
+ "ণ": 29,
35
+ "ত": 30,
36
+ "থ": 31,
37
+ "দ": 32,
38
+ "ধ": 33,
39
+ "ন": 34,
40
+ "প": 35,
41
+ "ফ": 36,
42
+ "ব": 37,
43
+ "ভ": 38,
44
+ "ম": 39,
45
+ "য": 40,
46
+ "র": 41,
47
+ "ল": 42,
48
+ "শ": 43,
49
+ "ষ": 44,
50
+ "স": 45,
51
+ "হ": 46,
52
+ "া": 47,
53
+ "ি": 48,
54
+ "ী": 49,
55
+ "ু": 50,
56
+ "ূ": 51,
57
+ "ৃ": 52,
58
+ "ে": 53,
59
+ "ৈ": 54,
60
+ "ো": 55,
61
+ "ৌ": 56,
62
+ "্": 57,
63
+ "ৎ": 58,
64
+ "ড়": 59,
65
+ "ঢ়": 60,
66
+ "য়": 61
67
+ }
68
+ }