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

Display, filter and search log messages in your terminal

Simple PyTorch implementations of Badnets on MNIST and CIFAR10.

PyTorch implementation of the Value Iteration Networks (VIN) (NIPS '16 best paper)

Detection of drones using their thermal signatures from thermal camera through YOLO-V3 based CNN with modifications to encapsulate drone motion

Data Augmentation Using Keras and Python

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

ExCon: Explanation-driven Supervised Contrastive Learning

GPU implementation of $k$-Nearest Neighbors and Shared-Nearest Neighbors

Minimal PyTorch implementation of Generative Latent Optimization from the paper "Optimizing the Latent Space of Generative Networks"

Experiments with Fourier layers on simulation data.

Birthday-problem - The birthday problem asks for the probability that, in a set of n randomly chosen people, at least two will share a birthday

PyTorch implementation of DUL (Data Uncertainty Learning in Face Recognition, CVPR2020)

Code to accompany the paper "Finding Bipartite Components in Hypergraphs", which is published in NeurIPS'21.

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.

U-Net implementation in PyTorch for FLAIR abnormality segmentation in brain MRI

An image classification app boilerplate to serve your deep learning models asap!

Can we learn gradients by Hamiltonian Neural Networks?

Real-world Anomaly Detection in Surveillance Videos- pytorch Re-implementation

Near-Optimal Sparse Allreduce for Distributed Deep Learning (published in PPoPP'22)

BT-Unet: A-Self-supervised-learning-framework-for-biomedical-image-segmentation-using-Barlow-Twins