shirain-he Goto Github PK

annotated_deep_learning_paper_implementations

🧑‍🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

bert-lid

Leveraging BERT to Improve Spoken Language Identification

blog

声音序列相似度

chinese-text-correction-papers

text correction papers

chinese_speech_pretrain

chinese speech pretrained models

craspell_pytorch

cs-wiki

📙 致力打造完善的后端知识体系. Not only an Interview-Guide, but also a Learning-Direction.

csc

ChineseBert用于中文拼写纠错

csc-without-readme

中文错别字识别与语法错误纠正

ctc-attention-mispronunciation

A Full Text-Dependent End to End Mispronunciation Detection and Diagnosis with Easy Data Augment Techniques

ernie-csc

Correcting Chinese Spelling Errors with Phonetic Pre-training 非官方实现

ernie-pytorch

ERNIE Pytorch Version

fay

Fay是一个完整的开源项目，包含Fay控制器及数字人模型，可灵活组合出不同的应用场景：虚拟主播、现场推销货、商品导购、语音助理、远程语音助理、数字人互动、数字人面试官及心理测评、贾维斯、Her。 开源项目，非产品试用！！！

funasr

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models.

kaldi-cslt

kaldi的迷你版本

learngit

Be used to learn about git and github

learnlatex

本仓库收录了Latex+Vscode+Zotero+Git论文撰写超级工具链的详细配置和使用说明，以及提供了本人实战的一篇用该工具撰写的论文可供测试。 希望能帮助到更多正在学习LaTeX的人，觉得有用的话也希望大家多多分享和Star!

listen-attend-spell-v2

PyTorch implementation of Listen Attend and Spell Automatic Speech Recognition (ASR).

lmchain

A large chinese freelanguage chain tools,you can get free API from:open.bigmodel.cn

machine-learning-algorithms-implemented-by-python

《统计学习方法》--李航 书中算法实现

neuralspeech

praat_scripts

Some basic praat scripts.

praatassist

This repo assist us to prrat-wave-mark-work.

simcse

EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

speller-bert

中文纠错

translators_cn

Zotero translator中文网页抓取插件

tutorial

Deeplearning Algorithms Tutorial

wekws

Production First and Production Ready End-to-End Keyword Spotting Toolkit

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

wenetspeech

A 10000+ hours dataset for Chinese speech recognition