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