Upload tokenizer
Browse files- added_tokens.json +2 -2
- special_tokens_map.json +16 -0
- tokenizer_config.json +3 -0
- vocab.json +44 -43
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 47,
|
3 |
+
"<s>": 46
|
4 |
}
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,20 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
"pad_token": "[PAD]",
|
|
|
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]",
|
tokenizer_config.json
CHANGED
@@ -1,9 +1,12 @@
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
|
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
|
|
5 |
"pad_token": "[PAD]",
|
6 |
"replace_word_delimiter_char": " ",
|
|
|
7 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
8 |
"unk_token": "[UNK]",
|
9 |
"word_delimiter_token": "|"
|
|
|
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": "|"
|
vocab.json
CHANGED
@@ -1,47 +1,48 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"PAD": 43,
|
4 |
"[UNK]": 44,
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"غ": 28,
|
28 |
-
"ف": 0,
|
29 |
"ق": 22,
|
30 |
-
"ل":
|
31 |
-
"م":
|
32 |
-
"ن":
|
33 |
-
"و":
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
|
|
|
|
|
|
|
|
47 |
}
|
|
|
1 |
{
|
2 |
+
"[PAD]": 45,
|
|
|
3 |
"[UNK]": 44,
|
4 |
+
"|": 0,
|
5 |
+
"ء": 1,
|
6 |
+
"ا": 2,
|
7 |
+
"ب": 3,
|
8 |
+
"ت": 4,
|
9 |
+
"ث": 5,
|
10 |
+
"ج": 6,
|
11 |
+
"ح": 7,
|
12 |
+
"خ": 8,
|
13 |
+
"د": 9,
|
14 |
+
"ذ": 10,
|
15 |
+
"ر": 11,
|
16 |
+
"ز": 12,
|
17 |
+
"س": 13,
|
18 |
+
"ش": 14,
|
19 |
+
"ص": 15,
|
20 |
+
"ض": 16,
|
21 |
+
"ط": 17,
|
22 |
+
"ظ": 18,
|
23 |
+
"ع": 19,
|
24 |
+
"غ": 20,
|
25 |
+
"ف": 21,
|
|
|
|
|
26 |
"ق": 22,
|
27 |
+
"ل": 23,
|
28 |
+
"م": 24,
|
29 |
+
"ن": 25,
|
30 |
+
"و": 26,
|
31 |
+
"ى": 27,
|
32 |
+
"ي": 28,
|
33 |
+
"ً": 29,
|
34 |
+
"ٓ": 30,
|
35 |
+
"ٹ": 31,
|
36 |
+
"پ": 32,
|
37 |
+
"چ": 33,
|
38 |
+
"ڈ": 34,
|
39 |
+
"ڑ": 35,
|
40 |
+
"ژ": 36,
|
41 |
+
"ک": 37,
|
42 |
+
"گ": 38,
|
43 |
+
"ں": 39,
|
44 |
+
"ھ": 40,
|
45 |
+
"ہ": 41,
|
46 |
+
"ی": 42,
|
47 |
+
"ے": 43
|
48 |
}
|