khanhld commited on
Commit
cf9cba1
1 Parent(s): f57c7c8
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
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", "processor_class": "Wav2Vec2Processor"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "g": 6, "h": 7, "i": 8, "k": 9, "l": 10, "m": 11, "n": 12, "o": 13, "p": 14, "r": 15, "s": 16, "t": 17, "u": 18, "v": 19, "y": 20, "à": 21, "á": 22, "ã": 23, "ê": 24, "ì": 25, "í": 26, "ó": 27, "ô": 28, "ú": 29, "đ": 30, "ĩ": 31, "ũ": 32, "ơ": 33, "ư": 34, "ạ": 35, "ả": 36, "ấ": 37, "ầ": 38, "ậ": 39, "ắ": 40, "ẳ": 41, "ế": 42, "ề": 43, "ể": 44, "ệ": 45, "ị": 46, "ọ": 47, "ồ": 48, "ỗ": 49, "ớ": 50, "ờ": 51, "ỡ": 52, "ợ": 53, "ủ": 54, "ừ": 55, "|": 0, "[UNK]": 56, "[PAD]": 57}