FG-transformer-TTS Fine-grained style control in transformer-based text-to-speech synthesis

Last update: Dec 30, 2022

Related tags

Overview

LST-TTS

Official implementation for the paper Fine-grained style control in transformer-based text-to-speech synthesis. Submitted to ICASSP 2022. Audio samples/demo for our system can be accessed here

Setting up submodules

git submodule update --init --recursive

Get the waveglow vocoder checkpoint from here (This is from the NVIDIA official WaveGlow repo).

Setup environment

See docker/Dockerfile for the packages need to be installed.

Dataset preprocessing

LJSpeech

python preprocess_LJSpeech.py --datadir LJSpeechDir --outputdir OutputDir

VCTK

Get the leading and trailing scilence marks from this repo, and put vctk-silences.0.92.txt in your VCTK dataset directory.

python preprocess_VCTK.py --datadir VCTKDir --outputdir Output_Train_Dir

python preprocess_VCTK.py --datadir VCTKDir --outputdir Output_Test_Dir --make_test_set

--make_test_set: specify this flag to process the speakers in the test set, otherwise only process training speakers.

Training

LJSpeech

python train_TTS.py --precision 16 \
                    --datadir FeatureDir \
                    --vocoder_ckpt_path WaveGlowCKPT_PATH \
                    --sampledir SampleDir \
                    --batch_size 128 \
                    --check_val_every_n_epoch 50 \
                    --use_guided_attn \
                    --training_step 250000 \
                    --n_guided_steps 250000 \
                    --saving_path Output_CKPT_DIR \
                    --datatype LJSpeech \
                    [--distributed]

--distributed: enable DDP multi-GPU training
--batch_size: batch size per GPU, scale down if you train with multi-GPU and want to keep the same batch size
--check_val_every_n_epoch: sample and validate every n epoch
--datadir: output directory of the preprocess scripts

VCTK

python train_TTS.py --precision 16 \
                    --datadir FeatureDir \
                    --vocoder_ckpt_path WaveGlowCKPT_PATH \
                    --sampledir SampleDir \
                    --batch_size 64 \
                    --check_val_every_n_epoch 50 \
                    --use_guided_attn \
                    --training_step 150000 \
                    --n_guided_steps 150000 \
                    --etts_checkpoint LJSpeech_Model_CKPT \
                    --saving_path Output_CKPT_DIR \
                    --datatype VCTK \
                    [--distributed]

--etts_checkpoint: the checkpoint path of pretrained model (on LJ Speech)

Synthesis

We provide examples for synthesis of the system in synthesis.py, you can adjust this script to your own usage. Example to run synthesis.py:

python synthesis.py --etts_checkpoint VCTK_Model_CKPT \
                    --sampledir SampleDir \
                    --datatype VCTK \
                    --vocoder_ckpt_path WaveGlowCKPT_PATH

FG-transformer-TTS Fine-grained style control in transformer-based text-to-speech synthesis

Related tags

Overview

LST-TTS

Setting up submodules

Setup environment

Dataset preprocessing

LJSpeech

VCTK

Training

LJSpeech

VCTK

Synthesis

Owner

Li-Wei Chen

A python program to hack instagram

An updated version of virtual model making

Learning where to learn - Gradient sparsity in meta and continual learning

Files for a tutorial to train SegNet for road scenes using the CamVid dataset

Code and results accompanying our paper titled Mixture Proportion Estimation and PU Learning: A Modern Approach at Neurips 2021 (Spotlight)

Official implementation of the paper 'High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network' in CVPR 2021

RoMa: A lightweight library to deal with 3D rotations in PyTorch.

[ICCV 2021] Target Adaptive Context Aggregation for Video Scene Graph Generation

Efficient electromagnetic solver based on rigorous coupled-wave analysis for 3D and 2D multi-layered structures with in-plane periodicity

Categorical Depth Distribution Network for Monocular 3D Object Detection

Large dataset storage format for Pytorch

PyTorch Lightning + Hydra. A feature-rich template for rapid, scalable and reproducible ML experimentation with best practices. ⚡🔥⚡

Fermi Problems: A New Reasoning Challenge for AI

State-of-the-art data augmentation search algorithms in PyTorch

Recognize numbers from an (28 x 28) image using neural networks

A hifiasm fork for metagenome assembly using Hifi reads.

A TensorFlow implementation of Neural Program Synthesis from Diverse Demonstration Videos

Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR

Pytorch implementation of Straight Sampling Network For Point Cloud Learning (ICIP2021).

Pacman-AI - AI project designed by UC Berkeley. Designed reflex and minimax agents for the game Pacman.