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>": 54, "</s>": 55}
|
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, "%": 2, "'": 3, "(": 4, ")": 5, "+": 6, ",": 7, "-": 8, ".": 9, "/": 10, "0": 11, "9": 12, "ա": 13, "բ": 14, "գ": 15, "դ": 16, "ե": 17, "զ": 18, "է": 19, "ը": 20, "թ": 21, "ժ": 22, "ի": 23, "լ": 24, "խ": 25, "ծ": 26, "կ": 27, "հ": 28, "ձ": 29, "ղ": 30, "ճ": 31, "մ": 32, "յ": 33, "ն": 34, "շ": 35, "ո": 36, "չ": 37, "պ": 38, "ջ": 39, "ռ": 40, "ս": 41, "վ": 42, "տ": 43, "ր": 44, "ց": 45, "ւ": 46, "փ": 47, "ք": 48, "օ": 49, "ֆ": 50, "և": 51, "|": 0, "[UNK]": 52, "[PAD]": 53}
|