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