jfealko commited on
Commit
8ec41cd
1 Parent(s): 7e6a61e

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
1
+ {"<s>": 55, "</s>": 56}
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
+ {"a": 1, "b": 2, "c": 3, "e": 4, "f": 5, "g": 6, "h": 7, "i": 8, "k": 9, "l": 10, "m": 11, "n": 12, "o": 13, "p": 14, "r": 15, "s": 16, "t": 17, "x": 18, "z": 19, "а": 20, "б": 21, "в": 22, "г": 23, "д": 24, "е": 25, "ж": 26, "з": 27, "и": 28, "й": 29, "к": 30, "л": 31, "м": 32, "н": 33, "о": 34, "п": 35, "р": 36, "с": 37, "т": 38, "у": 39, "ф": 40, "х": 41, "ц": 42, "ч": 43, "ш": 44, "щ": 45, "ъ": 46, "ы": 47, "ь": 48, "э": 49, "ю": 50, "я": 51, "ё": 52, "|": 0, "[UNK]": 53, "[PAD]": 54}