jackaduma / Cyclegan Vc2
Licence: mit
Voice Conversion by CycleGAN (语音克隆/语音转换): CycleGAN-VC2
Stars: ✭ 158
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Cyclegan Vc2
Paddlegan
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.
Stars: ✭ 4,987 (+3056.33%)
Mutual labels: gan, pix2pix, cyclegan
Cyclegan
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Stars: ✭ 10,933 (+6819.62%)
Mutual labels: gan, pix2pix, cyclegan
Ai Art
PyTorch (and PyTorch Lightning) implementation of Neural Style Transfer, Pix2Pix, CycleGAN, and Deep Dream!
Stars: ✭ 153 (-3.16%)
Mutual labels: deeplearning, pix2pix, cyclegan
Pytorch Cyclegan And Pix2pix
Image-to-Image Translation in PyTorch
Stars: ✭ 16,477 (+10328.48%)
Mutual labels: gan, pix2pix, cyclegan
Sketch To Art
🖼 Create artwork from your casual sketch with GAN and style transfer
Stars: ✭ 115 (-27.22%)
Mutual labels: gan, pix2pix
Deepnudecli
DeepNude Command Line Version With Watermark Removed
Stars: ✭ 112 (-29.11%)
Mutual labels: gan, pix2pix
Awesome Gan For Medical Imaging
Awesome GAN for Medical Imaging
Stars: ✭ 1,814 (+1048.1%)
Mutual labels: gan, deeplearning
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (-36.71%)
Mutual labels: gan, deeplearning
Vocgan
VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network
Stars: ✭ 158 (+0%)
Mutual labels: gan, speech-synthesis
Ganotebooks
wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch
Stars: ✭ 1,446 (+815.19%)
Mutual labels: pix2pix, cyclegan
Tensorflow Pix2pix
A lightweight pix2pix Tensorflow implementation.
Stars: ✭ 143 (-9.49%)
Mutual labels: gan, pix2pix
Zi2zi
Learning Chinese Character style with conditional GAN
Stars: ✭ 1,988 (+1158.23%)
Mutual labels: deeplearning, pix2pix
Tensorflow2.0 Examples
🙄 Difficult algorithm, Simple code.
Stars: ✭ 1,397 (+784.18%)
Mutual labels: gan, pix2pix
Focal Frequency Loss
Focal Frequency Loss for Generative Models
Stars: ✭ 141 (-10.76%)
Mutual labels: gan, pix2pix
Pix2pixbegan.pytorch
A pytorch implementation of pix2pix + BEGAN (Boundary Equilibrium Generative Adversarial Networks)
Stars: ✭ 148 (-6.33%)
Mutual labels: gan, pix2pix
Cyclegan tensorlayer
Re-implement CycleGAN in Tensorlayer
Stars: ✭ 86 (-45.57%)
Mutual labels: gan, cyclegan
Specgan
SpecGAN - generate audio with adversarial training
Stars: ✭ 92 (-41.77%)
Mutual labels: gan, deeplearning
CycleGAN-VC2-PyTorch
This code is a PyTorch implementation for paper: CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion, a nice work on Voice-Conversion/Voice Cloning.
- [x] Dataset
- [ ] VC
- [x] Chinese Male Speakers (S0913 from AISHELL-Speech & GaoXiaoSong: a Chinese star)
- [x] Usage
- [x] Training
- [x] Example
- [ ] Demo
- [x] Reference
Update
2020.11.17: fixed issues: re-implements the second step adverserial loss.
2020.08.27: add the second step adverserial loss by Jeffery-zhang-nfls
CycleGAN-VC2
Project Page
To advance the research on non-parallel VC, we propose CycleGAN-VC2, which is an improved version of CycleGAN-VC incorporating three new techniques: an improved objective (two-step adversarial losses), improved generator (2-1-2D CNN), and improved discriminator (Patch GAN).
This repository contains:
- model code which implemented the paper.
- audio preprocessing script you can use to create cache for training data.
- training scripts to train the model.
- Examples of Voice Conversion - converted result after training.
Table of Contents
Requirement
pip install -r requirements.txt
Usage
preprocess
python preprocess_training.py
is short for
python preprocess_training.py --train_A_dir ./data/S0913/ --train_B_dir ./data/gaoxiaosong/ --cache_folder ./cache/
train
python train.py
is short for
python train.py --logf0s_normalization ./cache/logf0s_normalization.npz --mcep_normalization ./cache/mcep_normalization.npz --coded_sps_A_norm ./cache/coded_sps_A_norm.pickle --coded_sps_B_norm ./cache/coded_sps_B_norm.pickle --model_checkpoint ./model_checkpoint/ --resume_training_at ./model_checkpoint/_CycleGAN_CheckPoint --validation_A_dir ./data/S0913/ --output_A_dir ./converted_sound/S0913 --validation_B_dir ./data/gaoxiaosong/ --output_B_dir ./converted_sound/gaoxiaosong/
Pretrained
a pretrained model which converted between S0913 and GaoXiaoSong
download from Google Drive <735MB>
Demo
Samples:
reference speaker A: S0913(./data/S0913/BAC009S0913W0351.wav)
reference speaker B: GaoXiaoSong(./data/gaoxiaosong/gaoxiaosong_1.wav)
speaker A's speech changes to speaker B's voice: Converted from S0913 to GaoXiaoSong (./converted_sound/S0913/BAC009S0913W0351.wav)
Reference
- CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion. Paper, Project
- Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks. Paper, Project
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. Paper, Project, Code
- Image-to-Image Translation with Conditional Adversarial Nets. Paper, Project, Code
Donation
If this project help you reduce time to develop, you can give me a cup of coffee :)
AliPay(支付宝)
WechatPay(微信)
License
MIT © Kun
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].