mmmmichaelzhang Goto Github PK

assem-vc

Official Code for Assem-VC @ICASSP2022

asteroid

The PyTorch-based audio source separation toolkit for researchers || Pretrained models available

audiodvp

AudioDVP:Photorealistic Audio-driven Video Portraits

audiomass

Free full-featured web-based audio & waveform editing tool

auxiliaryasr

Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)

bark

🔊 Text-Prompted Generative Audio Model

cmgan

Conformer-based Metric GAN for speech enhancement

cross-lingual-voice-cloning

Tacotron 2 - PyTorch implementation with faster-than-realtime inference modified to enable cross lingual voice cloning.

deepfilternet

Noise supression using deep filtering

demucs

Code for the paper Hybrid Spectrogram and Waveform Source Separation

facial

FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute Learning. ICCV, 2021.

fastvc

A simple voice conversion tool

fullsubnet-plus

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

gpt-sovits

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

gulaerchen.github.io

matchering

🎚️ Open Source Audio Matching and Mastering

mellotron

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

mir-svc

Unsupervised WaveNet-based Singing Voice Conversion Using Pitch Augmentation and Two-phase Approach

mockingbird

🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

neuralsvb

Learning the Beauty in Songs: Neural Singing Voice Beautifier; ACL 2022 (Main conference); Official code

neuralvoicepuppetry

This github contains the network architectures of NeuralVoicePuppetry.

nonparaseq2seqvc_code

Implementation code of non-parallel sequence-to-sequence VC

nvc-net

parallelwavegan

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

pitchextractor

Deep Neural Pitch Extractor for Voice Conversion and TTS Training

randomcnn-voice-transfer

Audio style transfer with shallow random parameters CNN. Result: https://soundcloud.com/mazzzystar/sets/speech-conversion-sample

retrieval-based-voice-conversion-webui

Voice data <= 10 mins can also be used to train a good VC model!

s2vc

so-vits-svc-fork

so-vits-svc fork with realtime support, improved interface and more features.

ssr_eval

Evaluation and Benchmarking of Speech Super-resolution Methods