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