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