Alternatives and similar repositories for libtorch_tokenizer

Users that are interested in libtorch_tokenizer are comparing it to the libraries listed below

• LeeJuly30 / BERTCpp
  implement bert in pure c++
  ☆36Updated 5 years ago
• LieluoboAi / radish
  C++ model train&inference framework
  ☆223Updated 6 years ago
• ymcui / Chinese-MobileBERT
  Chinese MobileBERT（中文MobileBERT模型）
  ☆98Updated 3 years ago
• dhpollack / huggingface_libtorch
  Minimal example of using a traced huggingface transformers model with libtorch
  ☆35Updated 5 years ago
• zejunwang1 / easytokenizer
  高性能文本 Tokenizer 库
  ☆32Updated 2 years ago
• thuwyh / InferLight
  lightweighted deep learning inference service framework
  ☆39Updated 4 years ago
• yanqiuxia / BERT-PreTrain
  不用tensorflow estimator，分别采用字mask和wwm mask在中文领域内finetune bert模型
  ☆24Updated 5 years ago
• mattzheng / py-kenlm-model
  python | 高效使用统计语言模型kenlm：新词发现、分词、智能纠错等
  ☆169Updated 6 years ago
• CLUEbenchmark / MobileQA
  离线端阅读理解应用 QA for mobile, Android & iPhone
  ☆60Updated 3 years ago
• Peter-Chou / transformer_cpp_tokenizers
  transformer tokenizers (e.g. BERT tokenizer) in C++ (WIP)
  ☆18Updated 3 years ago
• tongchangD / bert_for_corrector
  基于bert进行中文文本纠错
  ☆240Updated 2 years ago
• CLUEbenchmark / PyCLUE
  Python toolkit for Chinese Language Understanding(CLUE) Evaluation benchmark
  ☆133Updated 2 years ago
• bojone / nezha_gpt_dialog
  ☆102Updated 5 years ago
• zhongerqiandan / pretrained-unilm-Chinese
  中文版unilm预训练模型
  ☆82Updated 4 years ago
• taishan1994 / Gector_chinese
  基于seq2edit (Gector) 的中文文本纠错。
  ☆29Updated 3 years ago
• ZhuiyiTechnology / roformer-v2
  RoFormer升级版
  ☆154Updated 3 years ago
• pogevip / BERT4TensorRT
  TensorRT
  ☆11Updated 5 years ago
• JovenChu / FasterTransformer_Bert
  Using FasterTransformer for accelerating the predict speed of bert and roberta
  ☆14Updated 6 years ago
• BitVoyage / FastBERT
  对ACL2020 FastBERT论文的复现，论文地址//arxiv.org/pdf/2004.02178.pdf
  ☆193Updated 4 years ago
• zhusleep / tagger_rewriter
  对话改写介绍文章
  ☆98Updated 2 years ago
• zejunwang1 / bert4vec
  一个基于预训练的句向量生成工具
  ☆138Updated 2 years ago
• zejunwang1 / darmatch
  一个非常高效的字符串匹配工具，支持正向/反向最大匹配分词和多模式字符串精确匹配
  ☆16Updated 2 years ago
• liushulinle / PLOME
  Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021
  ☆240Updated 3 years ago
• jiangtaojy / mlm_bert_traning
  基于mlm方式的带有纠错功能的拼音转汉字bert预训练模型，pinyin correcter，基于pytorch框架实现
  ☆47Updated 5 years ago
• charlesXu86 / char_featurizer
  汉字字符特征提取工具，可以提取出字符中的字音（声母、韵母、声调）、字形（偏旁、部首）、四角编码等特征，同时可作为tensor输入到模型
  ☆138Updated 5 years ago
• jiangnanboy / intent_detection_and_slot_filling
  intent detection and slot filling 意图识别与槽填充联合模型
  ☆44Updated 3 years ago
• wptoux / albert-chinese-large-webqa
  基于百度webqa与dureader数据集训练的Albert Large QA模型
  ☆77Updated 5 years ago
• qiufengyuyi / bert-of-theseus-tf
  tensorflow version of bert-of-theseus
  ☆63Updated 5 years ago
• HillZhang1999 / CTC-Report
  CTC2021-中文文本纠错大赛的SOTA方案及在线演示
  ☆73Updated 2 years ago
• pluto-junzeng / C4-zh
  大规模中文语料
  ☆44Updated 6 years ago