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 |
+
{"ر": 0, "ف": 2, "و": 3, "ا": 4, "ے": 5, "ں": 6, "س": 7, "ق": 8, "ک": 9, "ش": 10, "غ": 11, "ن": 12, "د": 13, "م": 14, "ڈ": 15, "ح": 16, "ی": 17, "گ": 18, "پ": 19, "ل": 20, "ت": 21, "ٹ": 22, "آ": 23, "ہ": 24, "ھ": 25, "|": 1, "[UNK]": 26, "[PAD]": 27}
|