scasutt commited on
Commit
ca08f76
1 Parent(s): 14dd176

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -1
  2. tokenizer_config.json +1 -1
  3. vocab.json +1 -1
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json CHANGED
@@ -1 +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"}
 
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 CHANGED
@@ -1 +1 @@
1
- {"r": 0, "ä": 1, "v": 2, "q": 3, "k": 4, "g": 5, "x": 6, "s": 7, "ü": 9, "c": 10, "h": 11, "ö": 12, "w": 13, "u": 14, "e": 15, "l": 16, "z": 17, "j": 18, "m": 19, "y": 20, "p": 21, "f": 22, "i": 23, "o": 24, "n": 25, "a": 26, "b": 27, "t": 28, "d": 29, "|": 8, "[UNK]": 30, "[PAD]": 31}
 
1
+ {"o": 0, "ö": 1, "f": 2, "e": 3, "ä": 4, "q": 5, "n": 6, "l": 7, "k": 8, "r": 9, "d": 10, "m": 11, "w": 12, "ü": 14, "j": 15, "i": 16, "x": 17, "g": 18, "t": 19, "p": 20, "s": 21, "h": 22, "c": 23, "u": 24, "v": 25, "a": 26, "z": 27, "b": 28, "y": 29, "|": 13, "[UNK]": 30, "[PAD]": 31}