add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 30, "</s>": 31}

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