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>": 73, "</s>": 74}
|
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 |
+
{"แ": 1, "แ": 2, "แ": 3, "แ": 4, "แ": 5, "แ
": 6, "แ": 7, "แ": 8, "แ": 9, "แ": 10, "แ": 11, "แ": 12, "แ": 13, "แ": 14, "แ": 15, "แ": 16, "แ": 17, "แ": 18, "แ": 19, "แ": 20, "แ": 21, "แ": 22, "แ": 23, "แ": 24, "แ": 25, "แ": 26, "แ": 27, "แ": 28, "แ": 29, "แ": 30, "แ ": 31, "แก": 32, "แข": 33, "แฅ": 34, "แง": 35, "แช": 36, "แซ": 37, "แฌ": 38, "แญ": 39, "แฎ": 40, "แฏ": 41, "แฑ": 42, "แถ": 43, "แท": 44, "แธ": 45, "แน": 46, "แบ": 47, "แป": 48, "แผ": 49, "แฝ": 50, "แพ": 51, "แฟ": 52, "แ": 53, "แ": 54, "แ": 55, "แ": 56, "แ": 57, "แ
": 58, "แ": 59, "แ": 60, "แ": 61, "แ": 62, "แ": 63, "แ": 64, "แ": 65, "แ": 66, "แ": 67, "แ": 68, "แ": 69, "แ": 70, "|": 0, "[UNK]": 71, "[PAD]": 72}
|