add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 36, "</s>": 37}

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 @@
+{"0": 1, "1": 2, "2": 3, "3": 4, "4": 5, "5": 6, "6": 7, "8": 8, "9": 9, "a": 10, "b": 11, "c": 12, "d": 13, "e": 14, "f": 15, "g": 16, "h": 17, "i": 18, "j": 19, "k": 20, "l": 21, "m": 22, "n": 23, "o": 24, "p": 25, "q": 36, "r": 27, "s": 28, "t": 29, "u": 30, "v": 31, "w": 32, "x": 36, "y": 34, "z": 35, "|": 0, "[UNK]": 36, "[PAD]": 37}