add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 40, "</s>": 41}

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 @@
+{"h": 1, "«": 2, "»": 3, "а": 4, "б": 5, "в": 6, "г": 7, "д": 8, "е": 9, "ж": 10, "з": 11, "и": 12, "й": 13, "к": 14, "л": 15, "м": 16, "н": 17, "о": 18, "п": 19, "р": 20, "с": 21, "т": 22, "у": 23, "ф": 24, "х": 25, "ц": 26, "ч": 27, "ш": 28, "ъ": 29, "ы": 30, "ь": 31, "э": 32, "ю": 33, "я": 34, "ё": 35, "ү": 36, "ө": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}