add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 44, "</s>": 45}

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 @@
+{"«": 1, "»": 2, "ç": 3, "ă": 4, "ĕ": 5, "а": 6, "б": 7, "в": 8, "г": 9, "д": 10, "е": 11, "ж": 12, "з": 13, "и": 14, "й": 15, "к": 16, "л": 17, "м": 18, "н": 19, "о": 20, "п": 21, "р": 22, "с": 23, "т": 24, "у": 25, "ф": 26, "х": 27, "ц": 28, "ч": 29, "ш": 30, "щ": 31, "ъ": 32, "ы": 33, "ь": 34, "э": 35, "ю": 36, "я": 37, "ҫ": 38, "ӑ": 39, "ӗ": 40, "ӳ": 41, "|": 0, "[UNK]": 42, "[PAD]": 43}