Commit
•
7bcfb78
1
Parent(s):
7f2cb93
Upload tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +47 -0
- vocab.json +46 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 45,
|
| 3 |
+
"<s>": 44
|
| 4 |
+
}
|
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 |
+
"42": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"43": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"44": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"45": {
|
| 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 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 43,
|
| 3 |
+
"[UNK]": 42,
|
| 4 |
+
"|": 0,
|
| 5 |
+
"«": 1,
|
| 6 |
+
"»": 2,
|
| 7 |
+
"،": 3,
|
| 8 |
+
"؛": 4,
|
| 9 |
+
"؟": 5,
|
| 10 |
+
"ئ": 6,
|
| 11 |
+
"ا": 7,
|
| 12 |
+
"ب": 8,
|
| 13 |
+
"ت": 9,
|
| 14 |
+
"ج": 10,
|
| 15 |
+
"خ": 11,
|
| 16 |
+
"د": 12,
|
| 17 |
+
"ر": 13,
|
| 18 |
+
"ز": 14,
|
| 19 |
+
"س": 15,
|
| 20 |
+
"ش": 16,
|
| 21 |
+
"غ": 17,
|
| 22 |
+
"ف": 18,
|
| 23 |
+
"ق": 19,
|
| 24 |
+
"ك": 20,
|
| 25 |
+
"ل": 21,
|
| 26 |
+
"م": 22,
|
| 27 |
+
"ن": 23,
|
| 28 |
+
"و": 24,
|
| 29 |
+
"ى": 25,
|
| 30 |
+
"ي": 26,
|
| 31 |
+
"پ": 27,
|
| 32 |
+
"چ": 28,
|
| 33 |
+
"ژ": 29,
|
| 34 |
+
"ڭ": 30,
|
| 35 |
+
"گ": 31,
|
| 36 |
+
"ھ": 32,
|
| 37 |
+
"ۆ": 33,
|
| 38 |
+
"ۇ": 34,
|
| 39 |
+
"ۈ": 35,
|
| 40 |
+
"ۋ": 36,
|
| 41 |
+
"ې": 37,
|
| 42 |
+
"ە": 38,
|
| 43 |
+
"—": 39,
|
| 44 |
+
"‹": 40,
|
| 45 |
+
"›": 41
|
| 46 |
+
}
|