Giter Site home page Giter Site logo

pitch-control-vits's Introduction

Introduction

  1. vits 오픈 소스를 활용하여 Pitch를 제어할 수 있는 모델을 구성하고, VCTK 데이터셋을 사용해 학습합니다.
  2. VCTK 데이터셋은 기본적으로 48kHz인 점을 감안하여 22kHz로 resampling할 수 있도록 utils.load_wav_to_torch()를 수정했습니다.
  3. conda 환경으로 진행해도 무방하지만 본 레포지토리에서는 docker 환경만 제공합니다. 기본적으로 ubuntu에 docker, nvidia-docker가 설치되었다고 가정합니다.
  4. GPU, CUDA 종류에 따라 Dockerfile 상단 torch image 수정이 필요할 수도 있습니다.
  5. VCTK 데이터셋은 ASR 모델을 활용한 Auto-preprocessing 과정을 거친 후 학습에 사용되었습니다.

Dataset

  1. download dataset - https://www.kaggle.com/datasets/showmik50/vctk-dataset

Docker build

  1. git clone https://github.com/choiHkk/pitch-control-vits.git
  2. cd /path/to/the/pitch-control-vits
  3. docker build --tag pitch-control-vits:latest .

Training

  1. nvidia-docker run -it --name 'pitch-control-vits' -v /path/to/pitch-control-vits:/home/work/pitch-control-vits --ipc=host --privileged pitch-control-vits:latest
  2. cd /home/work/pitch-control-vits/monotonic_align
  3. python setup.py build_ext --inplace
  4. cd /home/work/pitch-control-vits
  5. python train_ms.py -c ./config/vctk_base_hifigan.json -m vctk_base_hifigan
  6. arguments
  • -c : config path
  • -m : model output directory
  1. (OPTIONAL) tensorboard --logdir=outdir/logdir

Tensorboard losses

pitch-control-vits-tensorboard-losses1 pitch-control-vits-tensorboard-losses2

Tensorboard Stats

pitch-control-vits-tensorboard-stats

Reference

  1. VITS
  2. VISinger
  3. Period-VITS
  4. FastSpeech2
  5. HiFi-GAN

pitch-control-vits's People

Contributors

choihkk avatar ailab-choihk avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.