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