add tokenizer

added_tokens.json

@@ -1 +1 @@
-{"<s>": 64, "</s>": 65}
+{"<s>": 63, "</s>": 64}

tokenizer_config.json

@@ -1 +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"}
+{"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

@@ -1 +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}
+{" ": 1, "(": 2, ")": 3, "a": 4, "b": 5, "c": 6, "e": 7, "f": 8, "g": 9, "h": 10, "i": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "r": 18, "s": 19, "t": 20, "x": 21, "z": 22, "«": 23, "»": 24, "а": 25, "б": 26, "в": 27, "г": 28, "д": 29, "е": 30, "ж": 31, "з": 32, "и": 33, "й": 34, "к": 35, "л": 36, "м": 37, "н": 38, "о": 39, "п": 40, "р": 41, "с": 42, "т": 43, "у": 44, "ф": 45, "х": 46, "ц": 47, "ч": 48, "ш": 49, "щ": 50, "ъ": 51, "ы": 52, "ь": 53, "э": 54, "ю": 55, "я": 56, "ё": 57, "‑": 58, "–": 59, "—": 60, "…": 61, "−": 62, "[UNK]": 62, "[PAD]": 63}