DrishtiSharma commited on
Commit
b65d721
1 Parent(s): c792642

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -0
  2. tokenizer_config.json +1 -0
  3. vocab.json +1 -0
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
1
+ {"(": 1, ")": 2, "/": 3, "a": 4, "b": 5, "c": 6, "d": 7, "e": 8, "f": 9, "g": 10, "h": 11, "i": 12, "j": 13, "k": 14, "l": 15, "m": 16, "n": 17, "o": 18, "p": 19, "q": 20, "r": 21, "s": 22, "t": 23, "u": 24, "v": 25, "w": 26, "x": 27, "y": 28, "z": 29, "«": 30, "»": 31, "½": 32, "à": 33, "â": 34, "ç": 35, "è": 36, "é": 37, "ê": 38, "ñ": 39, "ô": 40, "ù": 41, "û": 42, "ü": 43, "ʼ": 44, "…": 45, "|": 0, "[UNK]": 46, "[PAD]": 47}