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

Read and write layered TIFF ImageSourceData and ImageResources tags

Code for reproducing our paper: LMSOC: An Approach for Socially Sensitive Pretraining

This is code of book "Learn Deep Learning with PyTorch"

Source code for CVPR 2021 paper "Riggable 3D Face Reconstruction via In-Network Optimization"

KwaiRec: A Fully-observed Dataset for Recommender Systems (Density: Almost 100%)

Github for the conference paper GLOD-Gaussian Likelihood OOD detector

Implementation of Hierarchical Transformer Memory (HTM) for Pytorch

chainladder - Property and Casualty Loss Reserving in Python

Software & Hardware to do multi color printing with Sharpies

This repository is for our EMNLP 2021 paper "Automated Generation of Accurate & Fluent Medical X-ray Reports"

Boundary IoU API (Beta version)

Emotion classification of online comments based on RNN

An OpenAI Gym environment for multi-agent car racing based on Gym's original car racing environment.

Implementation of the paper "Language-agnostic representation learning of source code from structure and context".

Official code for "EagerMOT: 3D Multi-Object Tracking via Sensor Fusion" [ICRA 2021]

PyTorch code accompanying the paper "Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning" (NeurIPS 2021).

Consecutive-Subsequence - Simple software to calculate susequence with highest sum

AOT (Associating Objects with Transformers) in PyTorch

CSD: Consistency-based Semi-supervised learning for object Detection

TensorFlow implementation of "TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?"