add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 64, "</s>": 65}

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, "a": 3, "b": 4, "c": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "r": 17, "s": 18, "t": 19, "x": 20, "z": 21, "«": 22, "»": 23, "а": 24, "б": 25, "в": 26, "г": 27, "д": 28, "е": 29, "ж": 30, "з": 31, "и": 32, "й": 33, "к": 34, "л": 35, "м": 36, "н": 37, "о": 38, "п": 39, "р": 40, "с": 41, "т": 42, "у": 43, "ф": 44, "х": 45, "ц": 46, "ч": 47, "ш": 48, "щ": 49, "ъ": 50, "ы": 51, "ь": 52, "э": 53, "ю": 54, "я": 55, "ё": 56, "‑": 57, "–": 58, "—": 59, "…": 60, "−": 61, "|": 0, "[UNK]": 62, "[PAD]": 63}