pritishyuvraj / Voice Conversion Gan
Licence: unlicense
Voice Conversion using Cycle GAN's For Non-Parallel Data
Stars: ✭ 82
Projects that are alternatives of or similar to Voice Conversion Gan
Facial Similarity With Siamese Networks In Pytorch
Implementing Siamese networks with a contrastive loss for similarity learning
Stars: ✭ 719 (+776.83%)
Mutual labels: jupyter-notebook, pytorch-tutorial
Relativistic Average Gan Keras
The implementation of Relativistic average GAN with Keras
Stars: ✭ 36 (-56.1%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Gans In Action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
Stars: ✭ 748 (+812.2%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Early Stopping Pytorch
Early stopping for PyTorch
Stars: ✭ 612 (+646.34%)
Mutual labels: jupyter-notebook, pytorch-tutorial
Animegan
A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing.
Stars: ✭ 1,095 (+1235.37%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Machine Learning
머신러닝 입문자 혹은 스터디를 준비하시는 분들에게 도움이 되고자 만든 repository입니다. (This repository is intented for helping whom are interested in machine learning study)
Stars: ✭ 705 (+759.76%)
Mutual labels: jupyter-notebook, pytorch-tutorial
Udacity Deep Learning Nanodegree
This is just a collection of projects that made during my DEEPLEARNING NANODEGREE by UDACITY
Stars: ✭ 15 (-81.71%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Generative Adversarial Networks
Introduction to generative adversarial networks, with code to accompany the O'Reilly tutorial on GANs
Stars: ✭ 505 (+515.85%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Keras Pytorch Avp Transfer Learning
We pit Keras and PyTorch against each other, showing their strengths and weaknesses in action. We present a real problem, a matter of life-and-death: distinguishing Aliens from Predators!
Stars: ✭ 42 (-48.78%)
Mutual labels: jupyter-notebook, pytorch-tutorial
Video Classification
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Stars: ✭ 543 (+562.2%)
Mutual labels: jupyter-notebook, pytorch-tutorial
Machine Learning
My Attempt(s) In The World Of ML/DL....
Stars: ✭ 78 (-4.88%)
Mutual labels: jupyter-notebook, pytorch-tutorial
Deep Learning With Pytorch Chinese
本仓库将PyTorch官方书籍《Deep learning with PyTorch》（基本摘录版）翻译成中文版并给出可运行的相关代码。
Stars: ✭ 517 (+530.49%)
Mutual labels: jupyter-notebook, pytorch-tutorial
Fewshot Face Translation Gan
Generative adversarial networks integrating modules from FUNIT and SPADE for face-swapping.
Stars: ✭ 705 (+759.76%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Hidt
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Stars: ✭ 513 (+525.61%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Multi Viewpoint Image Generation
Given an image and a target viewpoint, generate synthetic image in the target viewpoint
Stars: ✭ 23 (-71.95%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Generative Models
Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN
Stars: ✭ 438 (+434.15%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Generative Adversarial Network Tutorial
Tutorial on creating your own GAN in Tensorflow
Stars: ✭ 461 (+462.2%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Yann
This toolbox is support material for the book on CNN (http://www.convolution.network).
Stars: ✭ 41 (-50%)
Mutual labels: jupyter-notebook, generative-adversarial-network
Vitech
tuyển chọn các tài liệu về công nghệ bằng tiếng Việt
Stars: ✭ 63 (-23.17%)
Mutual labels: jupyter-notebook, pytorch-tutorial
Voice-Conversion-GAN
Voice Conversion using Cycle GAN's (PyTorch Implementation). Architecture of the Cycle GAN is as follows:
Dependencies
- Python 3.5
- Numpy 1.14
- PyTorch 0.4.1
- ProgressBar2 3.37.1
- LibROSA 0.6
- FFmpeg 4.0
- PyWorld
Usage
Download Dataset
Download and unzip VCC2016 dataset to designated directories.
$ python download.py --help
usage: download.py [-h] [--download_dir DOWNLOAD_DIR] [--data_dir DATA_DIR]
[--datasets DATASETS]
optional arguments:
-h, --help show this help message and exit
--download_dir DOWNLOAD_DIR
Download directory for zipped data
--data_dir DATA_DIR Data directory for unzipped data
--datasets DATASETS Datasets available: vcc2016
For example, to download the datasets to download directory and extract to data directory:
$ python download.py --download_dir ./download --data_dir ./data --datasets vcc2016
Preprocessing for Training
Preprocess voice data and stores it in numpy format in ../cache folder
$ python prepocess_training.py --help
Usage: preprocess_training.py [-h] [--train_A_dir TRAIN_A_DIR]
[--train_B_dir TRAIN_B_DIR]
[--cache_folder CACHE_FOLDER]
Prepare data for training Cycle GAN using PyTorch
optional arguments:
-h, --help show this help message and exit
--train_A_dir TRAIN_A_DIR
Directory for source voice sample
--train_B_dir TRAIN_B_DIR
Directory for target voice sample
--cache_folder CACHE_FOLDER
Store preprocessed data in cache folders
For example, to train CycleGAN model for voice Conversion between SF1 and TM1:
$ python prepocess_training.py --train_A_dir ../data/vcc2016_training/SF1
--train_B_dir ../data/vcc2016_training/TM1
--cache_folder ../cache/
Train Model
$python train.py --help
usage: train.py [-h] [--logf0s_normalization LOGF0S_NORMALIZATION]
[--mcep_normalization MCEP_NORMALIZATION]
[--coded_sps_A_norm CODED_SPS_A_NORM]
[--coded_sps_B_norm CODED_SPS_B_NORM]
[--model_checkpoint MODEL_CHECKPOINT]
[--resume_training_at RESUME_TRAINING_AT]
[--validation_A_dir VALIDATION_A_DIR]
[--output_A_dir OUTPUT_A_DIR]
[--validation_B_dir VALIDATION_B_DIR]
[--output_B_dir OUTPUT_B_DIR]
Train CycleGAN using source dataset and target dataset
optional arguments:
-h, --help show this help message and exit
--logf0s_normalization LOGF0S_NORMALIZATION
Cached location for log f0s normalized
--mcep_normalization MCEP_NORMALIZATION
Cached location for mcep normalization
--coded_sps_A_norm CODED_SPS_A_NORM
mcep norm for data A
--coded_sps_B_norm CODED_SPS_B_NORM
mcep norm for data B
--model_checkpoint MODEL_CHECKPOINT
location where you want to save the odel
--resume_training_at RESUME_TRAINING_AT
Location of the pre-trained model to resume training
--validation_A_dir VALIDATION_A_DIR
validation set for sound source A
--output_A_dir OUTPUT_A_DIR
output for converted Sound Source A
--validation_B_dir VALIDATION_B_DIR
Validation set for sound source B
--output_B_dir OUTPUT_B_DIR
Output for converted sound Source B
For example, to train CycleGAN model for voice conversion between SF1 and TF2:
$python train.py --logf0s_normalization ../cache/logf0s_normalization.npz --mcep_normalization ../cache/mcep_normalization.npz --coded_sps_A_norm coded_sps_A_norm --coded_sps_B_norm coded_sps_B_norm --resume_training_at ../cache/model_checkpoint/_CycleGAN_CheckPoint --validation_A_dir ../data/vcc2016_training/evaluation_all/SF1/ --output_A_dir ../data/vcc2016_training/converted_sound/SF1 --validation_B_dir ../data/vcc2016_training/evaluation_all/TF2/ --output_B_dir ../data/vcc2016_training/converted_sound/TF2/
Reference
- Takuhiro Kaneko, Hirokazu Kameoka. Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks. 2017. (Voice Conversion CycleGAN)
- TensorFLow Implementation
To-Do List
- [x] CPU compatible
- [ ] Sample Outputs
- [ ] Evaluation Metrics
Useful Tutorials
PyTorch Tutorial: https://github.com/yunjey/pytorch-tutorial
Gaussian Mixture Model Voice Conversion: https://r9y9.github.io/nnmnkwii/latest/nnmnkwii_gallery/notebooks/vc/01-GMM%20voice%20conversion%20(en).html
CycleGAN - VC: http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/cyclegan-vc/
Voice Conversion using Variational Auto-Encoder: https://github.com/JeremyCCHsu/vae-npvc
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].