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