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

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)

Python scripts for performing road segemtnation and car detection using the HybridNets multitask model in ONNX.

Exploring Cross-Image Pixel Contrast for Semantic Segmentation

HandTailor: Towards High-Precision Monocular 3D Hand Recovery

Hack Camera, Microphone, Location, Clipboard With Just a Link. Also, Get Many Details About Victim's Device. And So On...

PyGRANSO: A PyTorch-enabled port of GRANSO with auto-differentiation

Mask2Former: Masked-attention Mask Transformer for Universal Image Segmentation in TensorFlow 2

Analyses of the individual electric field magnitudes with Roast.

This computer program provides a reference implementation of Lagrangian Monte Carlo in metric induced by the Monge patch

SGoLAM - Simultaneous Goal Localization and Mapping

State of the art Semantic Sentence Embeddings

PPLNN is a Primitive Library for Neural Network is a high-performance deep-learning inference engine for efficient AI inferencing

Pytorch implementation for "Adversarial Robustness under Long-Tailed Distribution" (CVPR 2021 Oral)

People Interaction Graph

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning

DeepMReye: magnetic resonance-based eye tracking using deep neural networks

Pytorch implementation of Learning Rate Dropout.

An open source Python package for plasma science that is under development

FluidNet re-written with ATen tensor lib