snehatyagi commited on
Commit
27922cf
·
1 Parent(s): a2dd820

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