jiangtaojy

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

Meaningful-GPT

something about基于gpt3.5/gpt4的实践应用

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

praat

Praat: Doing Phonetics By Computer

faiss

A library for efficient similarity search and clustering of dense vectors.

awesome-elasticsearch

A curated list of the most important and useful resources about elasticsearch: articles, videos, blogs, tips and tricks, use cases. All about Elasticsearch!

bertsearch

Elasticsearch with BERT for advanced document search.

FastSpeech2

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

aishell-3-baseline-fc

The code for aishell-3 baseline acoustic model

Resemblyzer

A python package to analyze and compare voices with deep learning

PyTorch_Speaker_Verification

PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.

Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

multi_speaker_tts

Implementation of Multi speaker TTS

tacotronv2_wavernn_chinese

tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)

ParallelWaveGAN

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

ASRFrame

An Automatic Speech Recognition Frame ，一个中文语音识别的完整框架， 提供了多个模型

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

sensitive-stop-words

互联网常用敏感词、停止词词库

ML-NLP

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。

PyTorchTricks

Some tricks of pytorch... :star:

JSONParser

linear-chain-crf

Implementation of a linear-chain CRF in PyTorch

ark-twokenize-py

Python port of the Twokenize class of ark-tweet-nlp

NLP-progress

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

bert

TensorFlow code and pre-trained models for BERT

transformers

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

vista-net

Code for the paper "VistaNet: Visual Aspect Attention Network for Multimodal Sentiment Analysis", AAAI'19

Tencent-Internship

腾讯实习生参考指南（非官方版）

CS-Notes

:books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计