wrice commited on
Commit
3fcfbc2
1 Parent(s): c12df92
preprocessor_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
- "processor_class": "Wav2Vec2ProcessorWithLM",
8
  "return_attention_mask": false,
9
  "sampling_rate": 16000
10
  }
 
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 CHANGED
@@ -1 +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}]}
 
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": " ", "special_tokens_map_file": "/home/will/.cache/huggingface/transformers/cbcde26dbfe5b924eb0ed1293d953a65f3f7054fa6f66b890a7dd2c1d6dcc3ed.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "name_or_path": "wrice/wavlm-large-timit-punctuation", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}
 
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 CHANGED
@@ -1 +1 @@
1
- {"g": 0, "s": 1, "V": 2, "c": 3, "?": 4, ",": 5, "K": 6, ":": 7, "p": 8, "h": 9, "j": 10, "t": 11, ";": 12, "u": 13, "k": 14, "Y": 15, "y": 16, "S": 17, "W": 18, "M": 19, "J": 20, "N": 21, "L": 22, "f": 23, "B": 24, "O": 25, "!": 26, "o": 27, "a": 28, "D": 29, "w": 30, "X": 31, "R": 32, "l": 33, "i": 34, ".": 35, "m": 36, "\"": 37, "d": 38, "T": 39, "q": 40, "b": 41, "n": 42, "G": 43, "z": 44, "F": 45, "P": 46, "H": 47, "e": 48, "I": 49, "Q": 50, "-": 51, "C": 52, "x": 53, "'": 54, "A": 55, "v": 56, "E": 57, "U": 58, "r": 59, "|": 60, "[UNK]": 61, "[PAD]": 62}
 
1
+ {"a": 0, "G": 1, ":": 2, "h": 3, "d": 4, "C": 5, "m": 6, "f": 7, "!": 8, ";": 9, "i": 10, "F": 11, "'": 12, "y": 13, "-": 14, "B": 15, "b": 16, "D": 17, ".": 18, "w": 19, "r": 20, "H": 22, "E": 23, "R": 24, "K": 25, "g": 26, "p": 27, "P": 28, "U": 29, "t": 30, "z": 31, "\"": 32, "T": 33, ",": 34, "I": 35, "N": 36, "l": 37, "u": 38, "k": 39, "x": 40, "A": 41, "V": 42, "s": 43, "e": 44, "J": 45, "q": 46, "n": 47, "X": 48, "S": 49, "L": 50, "W": 51, "o": 52, "v": 53, "?": 54, "O": 55, "Y": 56, "Q": 57, "j": 58, "c": 59, "M": 60, "|": 21, "[UNK]": 61, "[PAD]": 62, "<s>": 63, "</s>": 64}