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 |
+
{"ك": 0, "ا": 2, "س": 3, "ر": 4, "ک": 5, "ج": 6, "غ": 7, "ى": 8, "ئ": 9, "ت": 10, "ن": 11, "ﻻ": 12, "ء": 13, "ل": 14, "ظ": 15, "ي": 16, "ث": 17, "ذ": 18, "ی": 19, "خ": 20, "و": 21, "د": 22, "ش": 23, "ة": 24, "ع": 25, "ؤ": 26, "ب": 27, "ص": 28, "ﺃ": 29, "ض": 30, "ط": 31, "ز": 32, "ھ": 33, "ف": 34, "ه": 35, "ق": 36, "ڨ": 37, "م": 38, "ح": 39, "|": 1, "[UNK]": 40, "[PAD]": 41}
|