snehatyagi commited on
Commit
1965fad
·
1 Parent(s): b228d88

add tokenizer

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