An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

Bilibili Downloader. 一款命令行式哔哩哔哩下载器.

streamlit-option-menu is a simple Streamlit component that allows users to select a single item from a list of options in a menu.

A secure authentication module to manage user access in a Streamlit application.

Stable Diffusion web UI

WebUI extension for ControlNet

Let us control diffusion models!

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.

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

Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)【安全加固，暂停交互，请耐心等待】

Integer and fixed point square root functions using only add, subtract and shifts

A personal gallery of streamlit apps and components.

A Streamlit component integrating Label Studio Frontend in Streamlit applications

The official PyTorch implementation of "FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement".

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

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

Windows desktop front end for Spleeter - AI source separation

An extension of thu-spmi/CAT which contains a full-fledged implementation of CTC-CRF for Tensorflow.

A CRF-based ASR Toolkit

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

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

Convolution layer with Winograd algorithm written in C/C++ (project made for Politecnico di Milano)

基于飞桨开发的虚拟主播

Converts .py to .exe using a simple graphical interface

公众号【清风Python】文章代码归档

Xournal++ is a handwriting notetaking software with PDF annotation support. Written in C++ with GTK3, supporting Linux (e.g. Ubuntu, Debian, Arch, SUSE), macOS and Windows 10. Supports pen input fr…

Speech Algorithms

语音增强传统方法

speech enhancement\speech seperation\sound source localization