add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 53, "</s>": 54}

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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"a": 1, "i": 2, "j": 3, "n": 4, "o": 5, "«": 6, "»": 7, "̆": 8, "а": 9, "б": 10, "в": 11, "г": 12, "д": 13, "е": 14, "ж": 15, "з": 16, "и": 17, "й": 18, "к": 19, "л": 20, "м": 21, "н": 22, "о": 23, "п": 24, "р": 25, "с": 26, "т": 27, "у": 28, "ф": 29, "х": 30, "ц": 31, "ч": 32, "ш": 33, "щ": 34, "ъ": 35, "ы": 36, "ь": 37, "э": 38, "ю": 39, "я": 40, "ё": 41, "ғ": 42, "ҙ": 43, "ҡ": 44, "ң": 45, "ҫ": 46, "ү": 47, "һ": 48, "ә": 49, "ө": 50, "|": 0, "[UNK]": 51, "[PAD]": 52}