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