saribalgar commited on
Commit
5596203
·
1 Parent(s): 0d66979

Upload 4 files

Browse files
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": ["m", "i", "e", "h", "p", "d", "o", "z", "l", "q", "r", "j", "a", "b", "k", "f", "u", "v", "c", "w", "g", "x", "'", " ", "y", "s", "n", "t", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
 
7
  "return_attention_mask": false,
8
  "sampling_rate": 16000
9
  }
 
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
  }
special_tokens_map.json CHANGED
@@ -1,6 +1 @@
1
- {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "[UNK]"
6
- }
 
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 CHANGED
@@ -1,10 +1 @@
1
- {
2
- "bos_token": "<s>",
3
- "do_lower_case": false,
4
- "eos_token": "</s>",
5
- "pad_token": "[PAD]",
6
- "replace_word_delimiter_char": " ",
7
- "tokenizer_class": "Wav2Vec2CTCTokenizer",
8
- "unk_token": "[UNK]",
9
- "word_delimiter_token": "|"
10
- }
 
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": "/root/.cache/huggingface/transformers/fe018b0661558cf92ff53f5e133cdbd4aaaa961c3d1b0c3375bc94110265f845.fea372b8528a479b7415f13ca4e27a2f5f3782cbb3f15b4d19bb3cbe734e8137", "name_or_path": "saribalgar/wav2vec2-base-timit-ms", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}