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