Commit ·
e6536d0
1
Parent(s): 86ef11e
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 |
+
{"گ": 0, "ٹ": 1, "ق": 2, "خ": 3, "ث": 4, "ض": 5, "س": 6, "ظ": 7, "": 8, "م": 9, "ص": 10, "ا": 11, "ع": 12, "ل": 13, "ہ": 14, "ّ": 15, "ڈ": 16, "ِ": 17, "د": 18, "ں": 19, "چ": 20, "آ": 21, "ژ": 22, "َ": 23, "ر": 24, "ط": 25, "غ": 26, "ف": 27, "ک": 28, "ذ": 29, "ی": 30, "ھ": 31, "ئ": 32, "ز": 33, "ے": 34, "ح": 35, "ت": 36, "ء": 37, "ؤ": 38, "پ": 39, "ش": 40, "ب": 41, "ڑ": 42, "و": 43, "ن": 44, "ٔ": 45, "ً": 46, "ج": 48, "ُ": 49, "|": 47, "[UNK]": 50, "[PAD]": 51}
|