wangtianrui

OldPeopleHome

:fire:智能养老院项目

HGCN

The official repo of "HGCN: Harmonic Gated Compensation Network For Speech Enhancement"

APC-SNR

Implementation of "A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement" by pytorch

My-notes

:books:学习随笔

MindSpore4Speech

Audio-Enhancement-via-ONMF

DPCRN_DNS3

Implementation of paper "DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement"

onnx-simplifier

Simplify your onnx model

versatile_audio_super_resolution

Versatile audio super resolution (any -> 48kHz) with AudioSR.

RUI_SE

The official repo of "A Refining Underlying Information Framework for Speech Enhancement"

AcademiCodec

AcademiCodec: An Open Source Audio Codec Model for Academic Research

asr_labs

ASR labs

BigVGAN

Unofficial pytorch implementation of BigVGAN: A Universal Neural Vocoder with Large-Scale Training

conditional-flow-matching

EnCodec_Trainer

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

paper2gui

Convert AI papers to GUI，Make it easy and convenient for everyone to use artificial intelligence technology。让每个人都简单方便的使用前沿人工智能技术

poolformer

PoolFormer: MetaFormer is Actually What You Need for Vision

QuadTreeAttention

QuadTree Attention for Vision Transformers (ICLR2022)

s3prl

Self-Supervised Speech Pre-training and Representation Learning Toolkit.

SDDNet

Coarse implement of the paper "A Simultaneous Denoising and Dereverberation Framework with Target Decoupling", On DNS-2020 dataset, the DNSMOS of first stage is 3.42 and second stage is 3.47.

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector, Language Classifier and Spoken Number Detector

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Uformer

Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation

UniSpeech

vits_chinese

vits chinese, tts chinese, tts mandarin 史上训练最简单，音质最好的语音合成系统，兼容性非常好的合成框架

VoiceLDM

VoiceLDM: Text-to-Speech with Environmental Context

voiceldm-data

wangtianrui.github.io

resume

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit