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