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