Commit ·
0a2692e
1
Parent(s): c033bad
Upload tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +50 -0
- tokenizer_config.json +14 -0
- vocab.json +47 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 46,
|
| 3 |
+
"<s>": 45
|
| 4 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"content": "<s>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "</s>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": true,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "<s>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": true,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "</s>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
}
|
| 45 |
+
],
|
| 46 |
+
"bos_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"pad_token": "[PAD]",
|
| 49 |
+
"unk_token": "[UNK]"
|
| 50 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
| 9 |
+
"replace_word_delimiter_char": " ",
|
| 10 |
+
"target_lang": null,
|
| 11 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 12 |
+
"unk_token": "[UNK]",
|
| 13 |
+
"word_delimiter_token": "|"
|
| 14 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
".": 41,
|
| 3 |
+
"[PAD]": 40,
|
| 4 |
+
"[UNK]": 39,
|
| 5 |
+
"|": 36,
|
| 6 |
+
"ء": 19,
|
| 7 |
+
"آ": 18,
|
| 8 |
+
"أ": 42,
|
| 9 |
+
"إ": 43,
|
| 10 |
+
"ئ": 44,
|
| 11 |
+
"ا": 26,
|
| 12 |
+
"ب": 9,
|
| 13 |
+
"ة": 14,
|
| 14 |
+
"ت": 15,
|
| 15 |
+
"ث": 1,
|
| 16 |
+
"ج": 17,
|
| 17 |
+
"ح": 8,
|
| 18 |
+
"خ": 33,
|
| 19 |
+
"د": 12,
|
| 20 |
+
"ذ": 10,
|
| 21 |
+
"ر": 27,
|
| 22 |
+
"ز": 11,
|
| 23 |
+
"س": 0,
|
| 24 |
+
"ش": 6,
|
| 25 |
+
"ص": 37,
|
| 26 |
+
"ض": 31,
|
| 27 |
+
"ط": 32,
|
| 28 |
+
"ظ": 20,
|
| 29 |
+
"ع": 4,
|
| 30 |
+
"غ": 30,
|
| 31 |
+
"ف": 28,
|
| 32 |
+
"ق": 3,
|
| 33 |
+
"ك": 25,
|
| 34 |
+
"ل": 5,
|
| 35 |
+
"م": 38,
|
| 36 |
+
"ن": 7,
|
| 37 |
+
"ه": 29,
|
| 38 |
+
"و": 22,
|
| 39 |
+
"ى": 24,
|
| 40 |
+
"ي": 2,
|
| 41 |
+
"َ": 23,
|
| 42 |
+
"ُ": 16,
|
| 43 |
+
"ِ": 13,
|
| 44 |
+
"ّ": 34,
|
| 45 |
+
"ْ": 35,
|
| 46 |
+
"ھ": 21
|
| 47 |
+
}
|