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