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": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"X": 0, "R": 1, "U": 2, "I": 3, "P": 4, "M": 6, "W": 7, "V": 8, "K": 9, "B": 10, "Z": 11, "L": 12, "S": 13, "E": 14, "T": 15, "J": 16, "D": 17, "C": 18, "G": 19, "O": 20, "'": 21, "H": 22, "Q": 23, "A": 24, "Y": 25, "N": 26, "F": 27, "|": 5, "[UNK]": 28, "[PAD]": 29}