add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 39, "</s>": 40}

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