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