drscotthawley commited on
Commit
0b9b8f6
1 Parent(s): 9fdb42a

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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"m": 0, "i": 1, "r": 2, "p": 3, "b": 4, "v": 5, "s": 6, "c": 8, "w": 9, "h": 10, "g": 11, "o": 12, "u": 13, "'": 14, "d": 15, "x": 16, "f": 17, "z": 18, "k": 19, "j": 20, "q": 21, "n": 22, "a": 23, "t": 24, "l": 25, "y": 26, "e": 27, "|": 7, "[UNK]": 28, "[PAD]": 29}