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