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