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 |
+
{"ذ": 0, "غ": 1, "م": 2, "ص": 3, "ر": 4, "ح": 5, "آ": 6, "ق": 7, "ٹ": 8, "َ": 9, "د": 10, "ّ": 11, "ش": 12, "ُ": 13, "ؤ": 14, "ط": 15, "ہ": 16, "ٔ": 17, "ج": 18, "ے": 20, "گ": 21, "ھ": 22, "": 23, "ع": 24, "پ": 25, "ی": 26, "ِ": 27, "ب": 28, "ک": 29, "ژ": 30, "و": 31, "ظ": 32, "ض": 33, "چ": 34, "خ": 35, "ئ": 36, "ت": 37, "ف": 38, "ء": 39, "ث": 40, "ن": 41, "ً": 42, "ڈ": 43, "ل": 44, "ز": 45, "ڑ": 46, "س": 47, "ں": 48, "ا": 49, "|": 19, "[UNK]": 50, "[PAD]": 51}
|