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