Umong commited on
Commit
b5f9308
1 Parent(s): 7df6d4a

Upload tokenizer

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