Commit ·
dc6144b
1
Parent(s): c1f9214
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, "چ": 1, "ن": 2, "ق": 3, "ب": 4, "ر": 5, "ں": 6, "ط": 7, "ھ": 8, "ژ": 9, "د": 10, "ے": 11, "ڈ": 12, "ِ": 13, "ئ": 14, "آ": 15, "ث": 16, "ٹ": 17, "ٔ": 18, "ح": 19, "َ": 20, "ل": 21, "س": 22, "ؤ": 23, "ء": 24, "پ": 25, "ہ": 26, "ا": 27, "غ": 28, "ّ": 29, "": 30, "ع": 31, "ش": 32, "ً": 33, "ڑ": 34, "ز": 35, "ذ": 36, "ض": 37, "ُ": 38, "ج": 39, "م": 41, "ف": 42, "خ": 43, "ک": 44, "ی": 45, "ظ": 46, "و": 47, "گ": 48, "ت": 49, "|": 40, "[UNK]": 50, "[PAD]": 51}
|