From 9e42551b7c097a4714fd8fc2c0382f14680bbece Mon Sep 17 00:00:00 2001 From: HUANYU XU <147359634+Huanshere@users.noreply.github.com> Date: Thu, 12 Sep 2024 15:18:31 +0800 Subject: [PATCH] Update step3_2_splitbymeaning.py --- core/step3_2_splitbymeaning.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/core/step3_2_splitbymeaning.py b/core/step3_2_splitbymeaning.py index 9c7ee327..634cc1dc 100644 --- a/core/step3_2_splitbymeaning.py +++ b/core/step3_2_splitbymeaning.py @@ -79,7 +79,7 @@ def parallel_split_sentences(sentences, max_length, max_workers, nlp, retry_atte for index, sentence in enumerate(sentences): # Use tokenizer to split the sentence tokens = tokenize_sentence(sentence, nlp) - print("Tokenization result:", tokens) + # print("Tokenization result:", tokens) num_parts = math.ceil(len(tokens) / max_length) if len(tokens) > max_length: future = executor.submit(split_sentence, sentence, num_parts, max_length, index=index, retry_attempt=retry_attempt)