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