Pinned Repositories
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
AutoGPT-2024.05
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
BERT-chinese-text-classification-and-deployment
简单高效的Bert中文文本分类模型开发和部署，CPU上毫秒级预测
Chinese-ASR-gitbook
工业级中文语音识别系统电子书
DeepSpeech
A TensorFlow implementation of Baidu's DeepSpeech architecture
deepspeech2_pinyin_recognize
基于百度2016年开源的deepspeech改写拼音识别训练工程
deepspeech2_tensorflow
基于baidu 2016年开源语音识别项目修改后端为tensorflow，rnn层为 双向GRU，ctc损失计算调用tensorflow内置模块实现中文语音识别，在清华开源数据上的测试准确率0.97.
Interview_Code
A collection of classic algorithm written test questions in the direction of big data and AI
langchain
🦜🔗 Build context-aware reasoning applications
OpenNRE
哈工大bert上fine turning ，中文人物关系抽取任务准确率0.97
taorui-plus's Repositories
taorui-plus/OpenNRE
哈工大bert上fine turning ，中文人物关系抽取任务准确率0.97
taorui-plus/Chinese-ASR-gitbook
工业级中文语音识别系统电子书
taorui-plus/BERT-chinese-text-classification-and-deployment
简单高效的Bert中文文本分类模型开发和部署，CPU上毫秒级预测
taorui-plus/deepspeech2_tensorflow
基于baidu 2016年开源语音识别项目修改后端为tensorflow，rnn层为 双向GRU，ctc损失计算调用tensorflow内置模块实现中文语音识别，在清华开源数据上的测试准确率0.97.
taorui-plus/Interview_Code
A collection of classic algorithm written test questions in the direction of big data and AI
taorui-plus/DeepSpeech
A TensorFlow implementation of Baidu's DeepSpeech architecture
taorui-plus/deepspeech2_pinyin_recognize
基于百度2016年开源的deepspeech改写拼音识别训练工程
taorui-plus/BERT-BiLSTM-CRF-NER
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
taorui-plus/ccks_baidu_entity_link
ccks baidu entity link 实体链接 第一名
taorui-plus/dcase20_task4
Baseline of DCASE 2020 task 4
taorui-plus/DeepSpeech-enhance
将百度DeepSpeech的keras后端由theano改为tensorflow，整合mozilla解码模块进行中文语音识别模型部署
taorui-plus/metavoice-src
Foundational model for human-like, expressive TTS
taorui-plus/recorder.js
*UNMAINTAINED* JavaScript library to record audio in browsers as used in the SoundCloud Javascript SDK.
taorui-plus/sherpa
Speech-to-text server framework with next-gen Kaldi
taorui-plus/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production