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