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