add tokenizer

special_tokens_map.json

@@ -1 +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}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -1 +1 @@
-{"$": 1, "0": 2, "1": 3, "2": 4, "3": 5, "4": 6, "5": 7, "6": 8, "7": 9, "8": 10, "9": 11, "a": 12, "b": 13, "c": 14, "d": 15, "e": 16, "f": 17, "g": 18, "h": 19, "i": 20, "j": 21, "k": 22, "l": 23, "m": 24, "n": 25, "o": 26, "p": 27, "q": 28, "r": 29, "s": 30, "t": 31, "u": 32, "v": 33, "w": 34, "x": 35, "y": 36, "z": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}
+{"b": 0, "i": 1, "c": 2, "f": 3, "s": 4, "y": 5, "w": 6, "q": 8, "d": 9, "j": 10, "u": 11, "k": 12, "m": 13, "g": 14, "'": 15, "n": 16, "o": 17, "z": 18, "h": 19, "p": 20, "a": 21, "t": 22, "v": 23, "e": 24, "x": 25, "r": 26, "l": 27, "|": 7, "[UNK]": 28, "[PAD]": 29}