liuhuang31

BM3D-Denoise

Using BM3D to denoise

g2pw_once

G2pw's inference speed is accelerated by about 8-10 times. Change loop generated predictive data to only once and model loop prediction becomes only once.

hifigan-sr

hifigan super-resolution 16/24 kHz to 48 kHz

HiFTNet-sr

HiFTNet super-resolution 16/24 kHz to 48 kHz

simple_mainColor

dcase17_cnn

Sound event detection using CNN for DCASE17 task3

tts-frontend-dataset

TTS FrontEnd DataSet: Polyphone / Prosody / TextNormalization

MyHeyGen

sound_event_detection_cnn

sound event detection based on CNN

sound_event_detection_dnn

sound event detection based on DNN

generative-ai-for-beginners

12 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

ChatGPT-Next-Web

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。

FAcodec

Training code for FAcodec presented in NaturalSpeech3

g2p_mix

megatts2

Unoffical implement of Megatts2

NativeDancer

make your charactor Dancing as Native style

ZMM-TTS

ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations