add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 42, "</s>": 43}

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": "/workspace/container_0/model/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"aa": 1, "ae": 2, "ah": 3, "aw": 4, "ay": 5, "b": 6, "ch": 7, "d": 8, "dh": 9, "dx": 10, "eh": 11, "er": 12, "ey": 13, "f": 14, "g": 15, "h#": 16, "hh": 17, "ih": 18, "iy": 19, "jh": 20, "k": 21, "l": 22, "m": 23, "n": 24, "ng": 25, "ow": 26, "oy": 27, "p": 28, "r": 29, "s": 30, "sh": 31, "t": 32, "th": 33, "uh": 34, "uw": 35, "v": 36, "w": 37, "y": 38, "z": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}