David Daijun Chen's repositories
DigitalSichuan_2020
本项目用于2020年首届数字四川创新赛
AI_classroom
This repo archives projects introduced in AI_classroom of Zhihu
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
autocut
用文本编辑器剪视频
bark
🔊 Text-Prompted Generative Audio Model
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
conformer
PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
docker-kaldi-gstreamer-server
Dockerfile for kaldi-gstreamer-server.
EfficientConformer
[ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition
elasticsearch-analysis-pinyin
This Pinyin Analysis plugin is used to do conversion between Chinese characters and Pinyin.
GNLHD
The R codes for construction GNLHD and its optimization. We can also construct a LHD and NLHD by the R codes. More details will be found in a coming paper, GNLHD and Its Optimization written by Daijun Chen and Shifeng Xiong
hexo-theme-fluid
:ocean: 一款 Material Design 风格的 Hexo 主题 / An elegant Material-Design theme for Hexo
HmmGPT
This repo was created to build HMM like GPT application, which can be used to generate text and pictures at the same time.
kaldi
kaldi-asr/kaldi is the official location of the Kaldi project.
kenlm
KenLM: Faster and Smaller Language Model Queries
LanguageModel_Fusion
Realization of different LM integration methods for RNN-T
Learning-ASR-by-Implementation
通过构建真实语音识别服务来展开语音识别的方方面面。
MockingBird
🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
NeMo
NeMo: a toolkit for conversational AI
pycorrector
pycorrector is a toolkit for text error correction. It was developed to facilitate the designing, comparing, and sharing of deep text error correction models.
pyjsgf
JSpeech Grammar Format (JSGF) compiler, matcher and parser package for Python.
PythonCourse
python from scratch
RecurrentGPT
Official Code for Paper: RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text
sequitur-g2p
This is a github repository of the abandonware Sequitur G2P by Bisani & Ney
Shape-Transfer-Bayesian-Optimization
This project aims to implement Shape Transfer Bayesian Optimization, and compare it with other existing transfer Bayesian Optimization Methods.
speech-to-text-nodejs
:microphone: Sample Node.js Application for the IBM Watson Speech to Text Service
Two_Sample_Test
This repo is created to archive experiment data for two sampling test
voice_cloning
Clone and transcribe your voice in 5 seconds and generate a synthesised continuation with GPT-2. Many new features compared to forked repo.
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit