Upload tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +22 -0
- tokenizer_config.json +13 -0
- vocab.json +110 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 109,
|
3 |
+
"<s>": 108
|
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 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
",": 69,
|
3 |
+
".": 22,
|
4 |
+
"0": 24,
|
5 |
+
"1": 50,
|
6 |
+
"2": 48,
|
7 |
+
"3": 25,
|
8 |
+
"4": 99,
|
9 |
+
"5": 42,
|
10 |
+
"6": 87,
|
11 |
+
"7": 105,
|
12 |
+
"8": 18,
|
13 |
+
"9": 64,
|
14 |
+
"[PAD]": 107,
|
15 |
+
"[UNK]": 106,
|
16 |
+
"a": 93,
|
17 |
+
"b": 73,
|
18 |
+
"c": 35,
|
19 |
+
"d": 43,
|
20 |
+
"e": 68,
|
21 |
+
"f": 75,
|
22 |
+
"g": 84,
|
23 |
+
"h": 77,
|
24 |
+
"i": 101,
|
25 |
+
"j": 19,
|
26 |
+
"k": 92,
|
27 |
+
"l": 5,
|
28 |
+
"m": 81,
|
29 |
+
"n": 103,
|
30 |
+
"o": 7,
|
31 |
+
"p": 45,
|
32 |
+
"q": 95,
|
33 |
+
"r": 102,
|
34 |
+
"s": 1,
|
35 |
+
"t": 12,
|
36 |
+
"u": 104,
|
37 |
+
"v": 16,
|
38 |
+
"w": 20,
|
39 |
+
"x": 3,
|
40 |
+
"y": 23,
|
41 |
+
"z": 11,
|
42 |
+
"|": 2,
|
43 |
+
"à": 83,
|
44 |
+
"á": 57,
|
45 |
+
"â": 80,
|
46 |
+
"ã": 54,
|
47 |
+
"è": 30,
|
48 |
+
"é": 78,
|
49 |
+
"ê": 37,
|
50 |
+
"ì": 14,
|
51 |
+
"í": 62,
|
52 |
+
"ò": 28,
|
53 |
+
"ó": 33,
|
54 |
+
"ô": 53,
|
55 |
+
"õ": 9,
|
56 |
+
"ù": 85,
|
57 |
+
"ú": 86,
|
58 |
+
"ý": 15,
|
59 |
+
"ă": 72,
|
60 |
+
"đ": 52,
|
61 |
+
"ĩ": 59,
|
62 |
+
"ũ": 49,
|
63 |
+
"ơ": 21,
|
64 |
+
"ư": 29,
|
65 |
+
"ạ": 97,
|
66 |
+
"ả": 51,
|
67 |
+
"ấ": 61,
|
68 |
+
"ầ": 63,
|
69 |
+
"ẩ": 55,
|
70 |
+
"ẫ": 79,
|
71 |
+
"ậ": 66,
|
72 |
+
"ắ": 41,
|
73 |
+
"ằ": 10,
|
74 |
+
"ẳ": 26,
|
75 |
+
"ẵ": 13,
|
76 |
+
"ặ": 4,
|
77 |
+
"ẹ": 40,
|
78 |
+
"ẻ": 17,
|
79 |
+
"ẽ": 88,
|
80 |
+
"ế": 65,
|
81 |
+
"ề": 58,
|
82 |
+
"ể": 90,
|
83 |
+
"ễ": 67,
|
84 |
+
"ệ": 44,
|
85 |
+
"ỉ": 96,
|
86 |
+
"ị": 98,
|
87 |
+
"ọ": 34,
|
88 |
+
"ỏ": 46,
|
89 |
+
"ố": 71,
|
90 |
+
"ồ": 0,
|
91 |
+
"ổ": 100,
|
92 |
+
"ỗ": 8,
|
93 |
+
"ộ": 70,
|
94 |
+
"ớ": 94,
|
95 |
+
"ờ": 47,
|
96 |
+
"ở": 89,
|
97 |
+
"ỡ": 31,
|
98 |
+
"ợ": 38,
|
99 |
+
"ụ": 27,
|
100 |
+
"ủ": 36,
|
101 |
+
"ứ": 32,
|
102 |
+
"ừ": 76,
|
103 |
+
"ử": 60,
|
104 |
+
"ữ": 39,
|
105 |
+
"ự": 6,
|
106 |
+
"ỳ": 91,
|
107 |
+
"ỷ": 74,
|
108 |
+
"ỹ": 56,
|
109 |
+
"₫": 82
|
110 |
+
}
|