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