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>": 50, "</s>": 51}
|
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"(": 1, ")": 2, "«": 3, "»": 4, "՛": 5, "՝": 6, "՞": 7, "ա": 8, "բ": 9, "գ": 10, "դ": 11, "ե": 12, "զ": 13, "է": 14, "ը": 15, "թ": 16, "ժ": 17, "ի": 18, "լ": 19, "խ": 20, "ծ": 21, "կ": 22, "հ": 23, "ձ": 24, "ղ": 25, "ճ": 26, "մ": 27, "յ": 28, "ն": 29, "շ": 30, "ո": 31, "չ": 32, "պ": 33, "ջ": 34, "ռ": 35, "ս": 36, "վ": 37, "տ": 38, "ր": 39, "ց": 40, "ւ": 41, "փ": 42, "ք": 43, "օ": 44, "ֆ": 45, "և": 46, "։": 47, "|": 0, "[UNK]": 48, "[PAD]": 49}
|