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

[MICCAI'20] AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes

Rl-quickstart - Reinforcement Learning Quickstart

The source code and data of the paper "Instance-wise Graph-based Framework for Multivariate Time Series Forecasting".

CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

An excellent hash algorithm combining classical sponge structure and RNN.

Neural style in TensorFlow! 🎨

Real-time object detection on Android using the YOLO network with TensorFlow

Rethinking the U-Net architecture for multimodal biomedical image segmentation

This repository contains a re-implementation of the code for the CVPR 2021 paper "Omnimatte: Associating Objects and Their Effects in Video."

Code of Classification Saliency-Based Rule for Visible and Infrared Image Fusion

Code to train models from "Paraphrastic Representations at Scale".

PAWS 🐾 Predicting View-Assignments with Support Samples

Learning Calibrated-Guidance for Object Detection in Aerial Images

A collection of 100 Deep Learning images and visualizations

(EI 2022) Controllable Confidence-Based Image Denoising

Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.

A simple pygame dino game which can also be trained and played by a NEAT KI

PolyTrack: Tracking with Bounding Polygons

List of papers, code and experiments using deep learning for time series forecasting

Machine learning notebooks in different subjects optimized to run in google collaboratory