add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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