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

vocab.json

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