Awesome speech/audio LLMs, representation learning, and codec models

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

Perceptual Quality Estimator for speech and audio

Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

So-VITS-SVC 本地部署/训练/推理/使用帮助文档 So-VITS-SVC Local Deployment/Training/Inference/Usage Help Document

DWT only with db1-db10 filters

this is an implementation of A Fast and Accurate Dependency Parser using Neural Networks(https://nlp.stanford.edu/pubs/emnlp2014-depparser.pdf) with pytorch

A Library of Audio Steganography & Watermarking Algorithms

SoftVC VITS Singing Voice Conversion

A Flow-based Generative Network for Speech Synthesis

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Audio steganalysis with tensorflow.

Audio steganalysis based on traditional handcrafted features design.

Mainly on text documents. Implemented a Mini Search Engine using different algorithms and then summaried documents using lexrank.

中山大学自然语言处理与知识图谱

🍲 好的，今天我们来做菜！OK, Let's Cook!

开发者边车，github打不开，github加速，git clone加速，git release下载加速，stackoverflow加速

武汉大学课程资料整理-WHU课代表计划

互联网首份程序员考公指南，由3位已经进入体制内的前大厂程序员联合献上。

LaTeX/XeLaTeX templates for academic publications: articles, dissertations, posters, and bachelor’s/master’s theses

Code-Audit-Challenges