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 |
+
{"ء": 1, "أ": 2, "ؤ": 3, "ئ": 4, "ا": 5, "ب": 6, "ة": 7, "ت": 8, "ث": 9, "ج": 10, "ح": 11, "خ": 12, "د": 13, "ذ": 14, "ر": 15, "ز": 16, "س": 17, "ش": 18, "ص": 19, "ض": 20, "ط": 21, "ظ": 22, "ع": 23, "غ": 24, "ف": 25, "ق": 26, "ك": 27, "ل": 28, "م": 29, "ن": 30, "ه": 31, "و": 32, "ى": 33, "ي": 34, "ٍ": 35, "|": 0, "[UNK]": 36, "[PAD]": 37}
|