Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +16 -0
- tokenizer_config.json +31 -0
- vocab.json +62 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<unk>": 60
|
3 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": {
|
3 |
+
"content": "|",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"unk_token": {
|
10 |
+
"content": "<unk>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
}
|
16 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_blank": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "|",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"60": {
|
13 |
+
"content": "<unk>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"clean_up_tokenization_spaces": true,
|
22 |
+
"is_uroman": false,
|
23 |
+
"language": "guj",
|
24 |
+
"model_max_length": 1000000000000000019884624838656,
|
25 |
+
"normalize": true,
|
26 |
+
"pad_token": "|",
|
27 |
+
"phonemize": false,
|
28 |
+
"tokenizer_class": "VitsTokenizer",
|
29 |
+
"unk_token": "<unk>",
|
30 |
+
"verbose": false
|
31 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
" ": 59,
|
3 |
+
"'": 47,
|
4 |
+
"-": 56,
|
5 |
+
"|": 0,
|
6 |
+
"ં": 10,
|
7 |
+
"ઃ": 54,
|
8 |
+
"અ": 28,
|
9 |
+
"આ": 26,
|
10 |
+
"ઇ": 49,
|
11 |
+
"ઈ": 30,
|
12 |
+
"ઉ": 42,
|
13 |
+
"ઊ": 48,
|
14 |
+
"ઋ": 57,
|
15 |
+
"એ": 29,
|
16 |
+
"ઐ": 58,
|
17 |
+
"ઓ": 27,
|
18 |
+
"ક": 9,
|
19 |
+
"ખ": 33,
|
20 |
+
"ગ": 32,
|
21 |
+
"ઘ": 44,
|
22 |
+
"ચ": 39,
|
23 |
+
"છ": 23,
|
24 |
+
"જ": 18,
|
25 |
+
"ઝ": 51,
|
26 |
+
"ઞ": 50,
|
27 |
+
"ટ": 36,
|
28 |
+
"ઠ": 45,
|
29 |
+
"ડ": 40,
|
30 |
+
"ઢ": 52,
|
31 |
+
"ણ": 22,
|
32 |
+
"ત": 3,
|
33 |
+
"થ": 19,
|
34 |
+
"દ": 25,
|
35 |
+
"ધ": 34,
|
36 |
+
"ન": 4,
|
37 |
+
"પ": 12,
|
38 |
+
"ફ": 43,
|
39 |
+
"બ": 31,
|
40 |
+
"ભ": 35,
|
41 |
+
"મ": 7,
|
42 |
+
"ય": 16,
|
43 |
+
"ર": 5,
|
44 |
+
"લ": 24,
|
45 |
+
"ળ": 37,
|
46 |
+
"વ": 13,
|
47 |
+
"શ": 21,
|
48 |
+
"ષ": 41,
|
49 |
+
"સ": 15,
|
50 |
+
"હ": 17,
|
51 |
+
"ા": 1,
|
52 |
+
"િ": 20,
|
53 |
+
"ી": 8,
|
54 |
+
"ુ": 14,
|
55 |
+
"ૂ": 38,
|
56 |
+
"ૃ": 46,
|
57 |
+
"ે": 2,
|
58 |
+
"ૈ": 53,
|
59 |
+
"ો": 11,
|
60 |
+
"ૌ": 55,
|
61 |
+
"્": 6
|
62 |
+
}
|