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

vocab.json

@@ -0,0 +1 @@
+{"т": 0, "и": 1, "у": 2, "р": 3, "ь": 4, "п": 5, "ф": 6, "с": 7, "й": 8, "л": 9, "е": 10, "м": 11, "а": 12, "щ": 13, "б": 14, "ж": 15, "ъ": 16, "х": 17, "я": 18, "э": 19, "о": 21, "г": 22, "д": 23, "в": 24, "ё": 25, "ш": 26, "к": 27, "ц": 28, "ю": 29, "з": 30, "н": 31, "ы": 32, "ч": 33, "|": 20, "[UNK]": 34, "[PAD]": 35}