update readMe

flagdata/quality_assessment/README.md

@@ -4,7 +4,7 @@ BERT and fasttext were chosen as evaluation models because they have the followi
 1. the BERT model performs well in text categorization and comprehension tasks, has strong language understanding and
    representation capabilities, and can effectively assess text quality.
 2. FastText models have efficient training and inference speeds while maintaining classification performance, which can
-   significantly reduce training and inference time.
+   significantly reduce training and inference time, version number 0.9.2 of fasttext
 
 The article compares different text categorization models including logistic regression, BERT and FastText to
 evaluate their performance. In the experiments, the BERTEval and FastText models perform well in text categorization

flagdata/quality_assessment/README_zh.md

@@ -2,7 +2,7 @@
 选择BERT和fasttext作为评估模型，是因为它们具有以下优点：
 
 1. BERT模型在文本分类和理解任务中表现出色，具有强大的语言理解和表示能力，能够有效地评估文本质量。
-2. FastText模型具有高效的训练和推理速度，同时保持分类性能，可以显著减少训练和推理时间。
+2. FastText模型具有高效的训练和推理速度，同时保持分类性能，可以显著减少训练和推理时间，fasttext的版本号0.9.2
 
 文章比较了不同的文本分类模型，包括逻辑回归、BERT和FastText，以评估它们的性能。在实验中，BERTEval和FastText模型在文本分类任务中表现良好，其中FastText模型在精度和召回率方面表现最佳。【实验结果来自ChineseWebText】
 

requirements.txt

@@ -25,7 +25,6 @@ effdet==0.4.1
 emoji==2.9.0
 et-xmlfile==1.1.0
 exceptiongroup==1.2.0
-fasttext==0.9.2
 filelock==3.13.1
 filetype==1.2.0
 flatbuffers==23.5.26