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

The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color

Code for Emergent Translation in Multi-Agent Communication

Sound Source Localization for AI Grand Challenge 2021

pytorch implementation of the ICCV'21 paper "MVTN: Multi-View Transformation Network for 3D Shape Recognition"

🐦 Quickly annotate data from the comfort of your Jupyter notebook

A New Approach to Overgenerating and Scoring Abstractive Summaries

Hybrid CenterNet - Hybrid-supervised object detection / Weakly semi-supervised object detection

A computer vision pipeline to identify the "icons" in Christian paintings

Code for Paper "Evidential Softmax for Sparse MultimodalDistributions in Deep Generative Models"

Physics-informed Neural Operator for Learning Partial Differential Equation

You Only Look Once for Panopitic Driving Perception

[NeurIPS 2021] ORL: Unsupervised Object-Level Representation Learning from Scene Images

This codebase proposes modular light python and pytorch implementations of several LiDAR Odometry methods

DISTIL: Deep dIverSified inTeractIve Learning.

SelfRemaster: SSL Speech Restoration

A curated list of long-tailed recognition resources.

This is a JAX implementation of Neural Radiance Fields for learning purposes.

Prototype for Baby Action Detection and Classification

NeRF visualization library under construction

Fully convolutional deep neural network to remove transparent overlays from images