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>": 57, "</s>": 58}
|
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, "a": 2, "b": 3, "c": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "k": 10, "l": 11, "m": 12, "n": 13, "o": 14, "p": 15, "r": 16, "s": 17, "t": 18, "x": 19, "z": 20, "а": 21, "б": 22, "в": 23, "г": 24, "д": 25, "е": 26, "ж": 27, "з": 28, "и": 29, "й": 30, "к": 31, "л": 32, "м": 33, "н": 34, "о": 35, "п": 36, "р": 37, "с": 38, "т": 39, "у": 40, "ф": 41, "х": 42, "ц": 43, "ч": 44, "ш": 45, "щ": 46, "ъ": 47, "ы": 48, "ь": 49, "э": 50, "ю": 51, "я": 52, "ё": 53, "‑": 54, "|": 0, "[UNK]": 55, "[PAD]": 56}
|