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