mrfirdauss commited on
Commit
8b9da68
·
verified ·
1 Parent(s): c795ebb

Update extractor.py

Browse files
Files changed (1) hide show
  1. extractor.py +0 -2
extractor.py CHANGED
@@ -68,8 +68,6 @@ def chunked_inference(text, tokenizer, model, max_length=512):
68
  tokens = tokenizer.tokenize(tok, is_split_into_words=True)
69
  # Initialize containers for tokenized inputs
70
  input_ids_chunks = []
71
- # Decode and print each token
72
- print(tokens)
73
  # Create chunks of tokens that fit within the model's maximum input size
74
  for i in range(0, len(tokens), max_length - 2): # -2 accounts for special tokens [CLS] and [SEP]
75
  chunk = tokens[i:i + max_length - 2]
 
68
  tokens = tokenizer.tokenize(tok, is_split_into_words=True)
69
  # Initialize containers for tokenized inputs
70
  input_ids_chunks = []
 
 
71
  # Create chunks of tokens that fit within the model's maximum input size
72
  for i in range(0, len(tokens), max_length - 2): # -2 accounts for special tokens [CLS] and [SEP]
73
  chunk = tokens[i:i + max_length - 2]