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