infinitejoy commited on
Commit
9d38db2
1 Parent(s): 90ae30c

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 31, "</s>": 32}
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"a": 1, "b": 2, "d": 3, "e": 4, "f": 5, "g": 6, "h": 7, "i": 8, "j": 9, "k": 10, "l": 11, "m": 12, "n": 13, "o": 14, "p": 15, "r": 16, "s": 17, "t": 18, "u": 19, "v": 20, "w": 21, "y": 22, "z": 23, "é": 24, "ñ": 25, "ô": 26, "̃": 27, "̈": 28, "|": 0, "[UNK]": 29, "[PAD]": 30}