此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

This is a repo for training and implementing the mobilenet-ssd v2 to tflite with c++ on x86 and arm64

TensorFlow Lite (tflite) C++ Series

Voice-based gender, age and language recognition.

Voice Gender Recognition/ Detection/ Identification using Deep Neural Networks and Machine Learning.

♂️♀️ Detect a person's gender from a voice file (90.7% +/- 1.3% accuracy).

Speech recognition module for Python, supporting several engines and APIs, online and offline.

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Simple embedded NLU for mobile apps

nlp模型转tensorflow lite，并使用c++调用

pytorch implementation for Patient Knowledge Distillation for BERT Model Compression

XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale

使用bert做领域分类、意图识别和槽位填充任务

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。

Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing

整理知识图谱相关学习资料