add tokenizer
Browse files- tokenizer_config.json +1 -1
- vocab.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
|
|
|
| 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
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"
|
|
|
|
| 1 |
+
{"": 0, "ح": 1, "ق": 2, "ل": 3, "ص": 4, "ذ": 5, "ژ": 7, "ا": 8, "ے": 9, "د": 10, "ہ": 11, "آ": 12, "ڑ": 13, "غ": 14, "ن": 15, "ب": 16, "ط": 17, "ر": 18, "ت": 19, "ز": 20, "ف": 21, "ٹ": 22, "ع": 23, "س": 24, "ی": 25, "و": 26, "ء": 27, "ش": 28, "ظ": 29, "ّ": 30, "ئ": 31, "ؤ": 32, "ک": 33, "ُ": 34, "ڈ": 35, "چ": 36, "ج": 37, "ں": 38, "م": 39, "ھ": 40, "پ": 41, "گ": 42, "خ": 43, "ض": 44, "ث": 45, "|": 6, "[UNK]": 46, "[PAD]": 47}
|