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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"ت": 0, "ذ": 1, "ق": 2, "ف": 3, "ئ": 4, "ٹ": 5, "ظ": 6, "ڈ": 7, "ک": 11, "ج": 9, "ا": 10, "ص": 12, "ھ": 14, "ہ": 15, "م": 16, "ر": 17, "ح": 18, "چ": 19, "ی": 20, "ء": 23, "گ": 24, "ے": 25, "آ": 26, "و": 27, "ڑ": 28, "ں": 29, "ض": 31, "پ": 32, "ل": 34, " ": 36, "ب": 37, "خ": 38, "س": 39, "ن": 27, "ؤ": 41, "ث": 42, "ط": 43, "ژ": 44, "غ": 45, "ش": 46, "ز": 47, "د": 48, "ع": 30, "[UNK]": 43, "[PAD]": 44}
|