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, "ل": 1, "ا": 2, "م": 3, "غ": 4, "ظ": 5, "ُ": 6, "ت": 7, "ج": 8, "ٔ": 9, "ڑ": 10, "خ": 11, "ے": 12, "ٹ": 13, "ڈ": 14, "ً": 15, "ی": 16, "د": 17, "ئ": 18, "َ": 19, "ر": 21, "و": 22, "آ": 23, "ِ": 24, "ث": 25, "چ": 26, "گ": 27, "ھ": 28, "ز": 29, "ّ": 30, "پ": 31, "ک": 32, "ض": 33, "ح": 34, "ش": 35, "ف": 36, "ص": 37, "ن": 38, "ط": 39, "س": 40, "ع": 41, "ژ": 42, "ہ": 43, "ں": 44, "ب": 45, "ؤ": 46, "ء": 47, "ذ": 48, "ق": 49, "|": 20, "[UNK]": 50, "[PAD]": 51}
|