NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling @ INTERSPEECH 2021

CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula Detection, MFD）、篇章分析（Layout Analysis）的Python3 包

类似按键精灵的鼠标键盘录制和自动化操作 模拟点击和键入 | automate mouse clicks and keyboard input

[.NET] m3u8 downloader 开源的命令行m3u8/HLS/dash下载器，支持普通AES-128-CBC解密，多线程，自定义请求头等. 支持简体中文,繁体中文和英文. English Supported.

A pytorch implementation of the paper "3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction" by Choy et al.

Single/multi view image(s) to voxel reconstruction using a recurrent neural network

通过可逆跳跃马尔科夫链蒙特卡洛方法实现一维大地电磁反演

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

High-Resolution Image Synthesis with Latent Diffusion Models

This research project aims at studying and finding a suitable method to implement audio bandwidth extension to bandlimited audio files.

Denoising Diffusion Probabilistic Models

A fast, high-quality neural vocoder.

TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis

iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier Transform

HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement

General Speech Restoration

General Speech Restoration

Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation implemented by Pytorch

《Pytorch模型训练实用教程》中配套代码

总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力

Unofficial PyTorch implementation of Google AI's VoiceFilter system

This is an official implementation of our NeurIPS 2021 paper "HRFormer: High-Resolution Transformer for Dense Prediction".

Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)

In defence of metric learning for speaker recognition

kaldi-asr/kaldi is the official location of the Kaldi project.

Speaker embedding(verification and recognition) using Pytorch

Keras implementation of ‘’Deep Speaker: an End-to-End Neural Speaker Embedding System‘’ (speaker recognition)

Generating room impulse responses