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

Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning

A solution to ensure Crowd Management with Contactless and Safe systems.

Image-Scaling Attacks and Defenses

MIM: MIM Installs OpenMMLab Packages

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems

This framework implements the data poisoning method found in the paper Adversarial Examples Make Strong Poisons

Learning to Simulate Dynamic Environments with GameGAN (CVPR 2020)

Object Database for Super Mario Galaxy 1/2.

Materials for upcoming beginner-friendly PyTorch course (work in progress).

Out of Distribution Detection on Natural Adversarial Examples

Abstractive opinion summarization system (SelSum) and the largest dataset of Amazon product summaries (AmaSum). EMNLP 2021 conference paper.

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

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

[ACL-IJCNLP 2021] "EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets"

Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception, IROS 2021

PConv-Keras - Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai

Open-sourcing the Slates Dataset for recommender systems research

PASSL包含 SimCLR，MoCo，BYOL，CLIP等基于对比学习的图像自监督算法以及 Vision-Transformer，Swin-Transformer，BEiT，CVT，T2T，MLP_Mixer等视觉Transformer算法

Implementation of the paper titled "Using Sampling to Estimate and Improve Performance of Automated Scoring Systems with Guarantees"