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": "[unq]", "pad_token": "[padded]", "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": "[unq]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[padded]", "do_lower_case": false, "word_delimiter_token": "|", "word_delimiter": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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