add tokenizer
Browse files- added_tokens.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>": 49, "</s>": 50}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
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": " ", "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"e": 1, "n": 2, "o": 3, "ء": 4, "آ": 5, "ؤ": 6, "ئ": 7, "ا": 8, "ب": 9, "ت": 10, "ث": 11, "ج": 12, "ح": 13, "خ": 14, "د": 15, "ذ": 16, "ر": 17, "ز": 18, "س": 19, "ش": 20, "ص": 21, "ض": 22, "ط": 23, "ظ": 24, "ع": 25, "غ": 26, "ف": 27, "ق": 28, "ل": 29, "م": 30, "ن": 31, "و": 32, "ٹ": 33, "پ": 34, "چ": 35, "ڈ": 36, "ڑ": 37, "ژ": 38, "ک": 39, "گ": 40, "ں": 41, "ھ": 42, "ہ": 43, "ۂ": 44, "ی": 45, "ے": 46, "|": 0, "[UNK]": 47, "[PAD]": 48}
|