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