Commit
•
ecfd107
1
Parent(s):
ac51d8f
Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +13 -0
- vocab.json +39 -0
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"2": 8,
|
| 3 |
+
"[PAD]": 36,
|
| 4 |
+
"[UNK]": 35,
|
| 5 |
+
"|": 9,
|
| 6 |
+
"ء": 0,
|
| 7 |
+
"ئ": 30,
|
| 8 |
+
"ا": 22,
|
| 9 |
+
"ب": 24,
|
| 10 |
+
"ة": 2,
|
| 11 |
+
"ت": 4,
|
| 12 |
+
"ث": 11,
|
| 13 |
+
"ج": 26,
|
| 14 |
+
"ح": 20,
|
| 15 |
+
"خ": 31,
|
| 16 |
+
"د": 7,
|
| 17 |
+
"ذ": 13,
|
| 18 |
+
"ر": 10,
|
| 19 |
+
"ز": 29,
|
| 20 |
+
"س": 33,
|
| 21 |
+
"ش": 14,
|
| 22 |
+
"ص": 19,
|
| 23 |
+
"ض": 3,
|
| 24 |
+
"ط": 12,
|
| 25 |
+
"ظ": 32,
|
| 26 |
+
"ع": 17,
|
| 27 |
+
"غ": 23,
|
| 28 |
+
"ف": 1,
|
| 29 |
+
"ق": 21,
|
| 30 |
+
"ك": 34,
|
| 31 |
+
"ل": 18,
|
| 32 |
+
"م": 27,
|
| 33 |
+
"ن": 16,
|
| 34 |
+
"ه": 6,
|
| 35 |
+
"و": 15,
|
| 36 |
+
"ى": 5,
|
| 37 |
+
"ي": 28,
|
| 38 |
+
"ڤ": 25
|
| 39 |
+
}
|