windowxiaoming

llama.cpp

LLM inference in C/C++

TTS

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

label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

conv_arithmetic

A technical report on convolution arithmetic in the context of deep learning

luci

LuCI - OpenWrt Configuration Interface

rnnoise

Recurrent neural network for audio noise reduction

glow

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

UER-py

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

libqrencode

A fast and compact QR Code encoding library

NJUCS

2023南京大学计算机科学与技术845考研公共课和专业课资料：数学一、英语一、政治、数据结构、计算机网络、计算机系统基础、操作系统教程、算法设计与分析-包括真题、期末考试、PPT、模拟题、专业课参考书及课后答案、报录比、经验等等

mellotron

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

glow-tts

A Generative Flow for Text-to-Speech via Monotonic Alignment Search

melgan

MelGAN vocoder (compatible with NVIDIA/tacotron2)

PESQ

PESQ (Perceptual Evaluation of Speech Quality) Wrapper for Python Users (narrow band and wide band)

vadnet

Real-time Voice Activity Detection in Noisy Eniviroments using Deep Neural Networks

voicebook

🗣️ A book and repo to get you started programming voice computing applications in Python (10 chapters and 200+ scripts).

ai-research-code

DailyTalk

Official repository of DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech, ICASSP 2023 (Oral)

resemble-unity-text-to-speech

Resemble's voice cloning engine within Unity

tacotron2-mandarin

Tensorflow implementation of Chinese/Mandarin TTS (Text-to-Speech) based on Tacotron-2 model.

online_calibration

This is an online calibration system between multiple sensors (camera, lidar, IMU). It is being created. . . . . .

Vinorm

Python - NSW package for Vietnamese: Normalization system to convert numbers, abbreviations, and words that cannot be pronounced into syllables

video_decode_ffmpeg

Video Decoder by ffmpeg, Solve the problem that the rtsp stream will receive some invalid frame when network is unstable.

EASY-EAI-Toolkit-C-Demo

EASY-EAI-Toolkit for EASY EAI NANO

ffmepgRtmp

利用opencv + FFmpeg实现直播推流

glow-tts-custom

ai-research-code

Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain

learnopencv

Learn OpenCV : C++ and Python Examples

Parallel-Tacotron2

PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling