add tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +22 -0
- tokenizer_config.json +12 -0
- vocab.json +87 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 86,
|
3 |
+
"<s>": 85
|
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 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"name_or_path": "./",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"replace_word_delimiter_char": " ",
|
8 |
+
"special_tokens_map_file": null,
|
9 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
10 |
+
"unk_token": "[UNK]",
|
11 |
+
"word_delimiter_token": "|"
|
12 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"!": 1,
|
3 |
+
"'": 2,
|
4 |
+
",": 3,
|
5 |
+
"-": 4,
|
6 |
+
".": 5,
|
7 |
+
":": 6,
|
8 |
+
";": 7,
|
9 |
+
"=": 8,
|
10 |
+
"?": 9,
|
11 |
+
"[PAD]": 84,
|
12 |
+
"[UNK]": 83,
|
13 |
+
"|": 0,
|
14 |
+
"।": 10,
|
15 |
+
"ঁ": 11,
|
16 |
+
"ং": 12,
|
17 |
+
"ঃ": 13,
|
18 |
+
"অ": 14,
|
19 |
+
"আ": 15,
|
20 |
+
"ই": 16,
|
21 |
+
"ঈ": 17,
|
22 |
+
"উ": 18,
|
23 |
+
"ঊ": 19,
|
24 |
+
"ঋ": 20,
|
25 |
+
"এ": 21,
|
26 |
+
"ঐ": 22,
|
27 |
+
"ও": 23,
|
28 |
+
"ঔ": 24,
|
29 |
+
"ক": 25,
|
30 |
+
"খ": 26,
|
31 |
+
"গ": 27,
|
32 |
+
"ঘ": 28,
|
33 |
+
"ঙ": 29,
|
34 |
+
"চ": 30,
|
35 |
+
"ছ": 31,
|
36 |
+
"জ": 32,
|
37 |
+
"ঝ": 33,
|
38 |
+
"ঞ": 34,
|
39 |
+
"ট": 35,
|
40 |
+
"ঠ": 36,
|
41 |
+
"ড": 37,
|
42 |
+
"ঢ": 38,
|
43 |
+
"ণ": 39,
|
44 |
+
"ত": 40,
|
45 |
+
"থ": 41,
|
46 |
+
"দ": 42,
|
47 |
+
"ধ": 43,
|
48 |
+
"ন": 44,
|
49 |
+
"প": 45,
|
50 |
+
"ফ": 46,
|
51 |
+
"ব": 47,
|
52 |
+
"ভ": 48,
|
53 |
+
"ম": 49,
|
54 |
+
"য": 50,
|
55 |
+
"র": 51,
|
56 |
+
"ল": 52,
|
57 |
+
"শ": 53,
|
58 |
+
"ষ": 54,
|
59 |
+
"স": 55,
|
60 |
+
"হ": 56,
|
61 |
+
"া": 57,
|
62 |
+
"ি": 58,
|
63 |
+
"ী": 59,
|
64 |
+
"ু": 60,
|
65 |
+
"ূ": 61,
|
66 |
+
"ৃ": 62,
|
67 |
+
"ে": 63,
|
68 |
+
"ৈ": 64,
|
69 |
+
"ো": 65,
|
70 |
+
"ৌ": 66,
|
71 |
+
"্": 67,
|
72 |
+
"ৎ": 68,
|
73 |
+
"ড়": 69,
|
74 |
+
"ঢ়": 70,
|
75 |
+
"য়": 71,
|
76 |
+
"০": 72,
|
77 |
+
"১": 73,
|
78 |
+
"২": 74,
|
79 |
+
"৩": 75,
|
80 |
+
"৪": 76,
|
81 |
+
"৫": 77,
|
82 |
+
"৬": 78,
|
83 |
+
"৭": 79,
|
84 |
+
"৮": 80,
|
85 |
+
"৯": 81,
|
86 |
+
"": 82
|
87 |
+
}
|