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