Commit ·
d34f74d
1
Parent(s): 91ae3dc
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 |
+
{"م": 0, "ظ": 1, "ٔ": 2, "ج": 3, "ؤ": 4, "گ": 5, "ض": 6, "ق": 7, "ِ": 8, "ش": 9, "ب": 10, "ُ": 11, "ے": 12, "ذ": 13, "پ": 14, "خ": 15, "ں": 16, "ح": 17, "ث": 18, "ف": 19, "ً": 20, "ڈ": 21, "ت": 22, "ہ": 23, "ّ": 24, "و": 25, "ک": 26, "ع": 27, "ز": 28, "س": 29, "چ": 30, "د": 31, "ی": 32, "ھ": 33, "ن": 34, "ژ": 35, "ڑ": 36, "َ": 37, "ا": 38, "آ": 39, "ء": 40, "ص": 41, "ل": 42, "غ": 43, "ٹ": 44, "ر": 45, "": 46, "ئ": 48, "ط": 49, "|": 47, "[UNK]": 50, "[PAD]": 51}
|