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>": 43, "</s>": 44}
|
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 |
+
{"-": 1, "ա": 2, "բ": 3, "գ": 4, "դ": 5, "ե": 6, "զ": 7, "է": 8, "ը": 9, "թ": 10, "ժ": 11, "ի": 12, "լ": 13, "խ": 14, "ծ": 15, "կ": 16, "հ": 17, "ձ": 18, "ղ": 19, "ճ": 20, "մ": 21, "յ": 22, "ն": 23, "շ": 24, "ո": 25, "չ": 26, "պ": 27, "ջ": 28, "ռ": 29, "ս": 30, "վ": 31, "տ": 32, "ր": 33, "ց": 34, "ւ": 35, "փ": 36, "ք": 37, "օ": 38, "ֆ": 39, "և": 40, "|": 0, "[UNK]": 41, "[PAD]": 42}
|