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