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