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