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