Upload tokenizer
Browse files- added_tokens.json +5 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +47 -0
- vocab.json +104 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 103,
|
3 |
+
"<s>": 102,
|
4 |
+
"[PAD]": 101
|
5 |
+
}
|
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 |
+
"100": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"101": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"102": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"103": {
|
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 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"&": 12,
|
3 |
+
"'": 20,
|
4 |
+
"[PAD]": 101,
|
5 |
+
"[UNK]": 100,
|
6 |
+
"a": 40,
|
7 |
+
"b": 33,
|
8 |
+
"c": 65,
|
9 |
+
"d": 41,
|
10 |
+
"e": 84,
|
11 |
+
"f": 14,
|
12 |
+
"g": 26,
|
13 |
+
"h": 13,
|
14 |
+
"i": 87,
|
15 |
+
"j": 91,
|
16 |
+
"k": 28,
|
17 |
+
"l": 86,
|
18 |
+
"m": 53,
|
19 |
+
"n": 5,
|
20 |
+
"o": 7,
|
21 |
+
"p": 39,
|
22 |
+
"q": 30,
|
23 |
+
"r": 19,
|
24 |
+
"s": 71,
|
25 |
+
"t": 75,
|
26 |
+
"u": 17,
|
27 |
+
"v": 46,
|
28 |
+
"w": 90,
|
29 |
+
"x": 16,
|
30 |
+
"y": 10,
|
31 |
+
"z": 97,
|
32 |
+
"|": 43,
|
33 |
+
"ँ": 32,
|
34 |
+
"ं": 23,
|
35 |
+
"ः": 38,
|
36 |
+
"अ": 42,
|
37 |
+
"आ": 2,
|
38 |
+
"इ": 36,
|
39 |
+
"ई": 80,
|
40 |
+
"उ": 62,
|
41 |
+
"ऊ": 100,
|
42 |
+
"ऋ": 24,
|
43 |
+
"ए": 98,
|
44 |
+
"ऐ": 55,
|
45 |
+
"ऑ": 47,
|
46 |
+
"ओ": 72,
|
47 |
+
"औ": 18,
|
48 |
+
"क": 63,
|
49 |
+
"ख": 1,
|
50 |
+
"ग": 9,
|
51 |
+
"घ": 15,
|
52 |
+
"च": 45,
|
53 |
+
"छ": 6,
|
54 |
+
"ज": 64,
|
55 |
+
"झ": 11,
|
56 |
+
"ञ": 4,
|
57 |
+
"ट": 34,
|
58 |
+
"ठ": 25,
|
59 |
+
"ड": 59,
|
60 |
+
"ढ": 37,
|
61 |
+
"ण": 27,
|
62 |
+
"त": 31,
|
63 |
+
"थ": 88,
|
64 |
+
"द": 48,
|
65 |
+
"ध": 8,
|
66 |
+
"न": 95,
|
67 |
+
"प": 92,
|
68 |
+
"फ": 57,
|
69 |
+
"ब": 68,
|
70 |
+
"भ": 99,
|
71 |
+
"म": 54,
|
72 |
+
"य": 73,
|
73 |
+
"र": 61,
|
74 |
+
"ल": 79,
|
75 |
+
"व": 85,
|
76 |
+
"श": 22,
|
77 |
+
"ष": 96,
|
78 |
+
"स": 51,
|
79 |
+
"ह": 50,
|
80 |
+
"़": 44,
|
81 |
+
"ा": 66,
|
82 |
+
"ि": 74,
|
83 |
+
"ी": 49,
|
84 |
+
"ु": 70,
|
85 |
+
"ू": 89,
|
86 |
+
"ृ": 69,
|
87 |
+
"ॅ": 76,
|
88 |
+
"े": 21,
|
89 |
+
"ै": 0,
|
90 |
+
"ॉ": 58,
|
91 |
+
"ो": 67,
|
92 |
+
"ौ": 94,
|
93 |
+
"्": 35,
|
94 |
+
"क़": 56,
|
95 |
+
"ख़": 78,
|
96 |
+
"ग़": 82,
|
97 |
+
"ज़": 29,
|
98 |
+
"ड़": 83,
|
99 |
+
"ढ़": 77,
|
100 |
+
"फ़": 93,
|
101 |
+
"।": 3,
|
102 |
+
"–": 52,
|
103 |
+
"’": 81
|
104 |
+
}
|