add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 50, "</s>": 51}

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