add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 52, "</s>": 53}

special_tokens_map.json

@@ -0,0 +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

@@ -0,0 +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

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