Morning's repositories
bert_punct
Punctuation restoration in ASR text
pycorrector
pycorrector is a toolkit for text error correction. It was developed to facilitate the designing, comparing, and sharing of deep text error correction models.
anomaly-detection-resources
Anomaly detection related books, papers, videos, and toolboxes
BERT-BiLSTM-CRF-NER
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
Chinese-Names-Corpus
中文人名语料库。人名生成器。中文姓名,姓氏,名字,称呼,日本人名,翻译人名,英文人名。可用于中文分词、人名实体识别。
chinese_text_normalization
Chinese text normalization for speech processing
cn-text-normalizer
A python module that convert chinese written string to read string. 一个python包:将中文书面字符串转换为口语字符串。
DeepXi
Deep Xi: A Deep Learning Approach to A Priori SNR Estimation. Used for Speech Enhancement and robust ASR.
DomainWords
SmoothNLP领域词汇示例 - 基于复旦公开新闻资讯库
Focal-Loss-Pytorch
全中文注释.(The loss function of retinanet based on pytorch).(You can use it on one-stage detection task or classifical task, to solve data imbalance influence).用于one-stage目标检测算法,提升检测效果.你也可以在分类任务中使用该损失函数,解决数据不平衡问题.
focal_loss_pytorch
A PyTorch Implementation of Focal Loss.
hangzhou_house_knowledge
2017年买房经历总结出来的买房购房知识分享给大家,希望对大家有所帮助。买房不易,且买且珍惜。Sharing the knowledge of buy an own house that according to the experience at hangzhou in 2017 to all the people. It's not easy to buy a own house, so I hope that it would be useful to everyone.
HarvestText
领域自适应文本挖掘工具(新词发现、情感分析、实体链接等),基于少量种子词和背景知识
jieba
结巴中文分词
MLAlgorithms
Minimal and clean examples of machine learning algorithms implementations
OpenNMT-py
Open Source Neural Machine Translation in PyTorch
pytorch-gradual-warmup-lr
Gradually-Warmup Learning Rate Scheduler for PyTorch
self-paced-ensemble
A general & effective ensemble framework for imbalance classification. | 泛用,高效,鲁棒的类别不平衡学习框架
TextNormSeq2Seq
Code and model files for paper: I. Lourentzou et al., Adapting Sequence to Sequence models for Text Normalization in Social Media", ICSWM'19
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.