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

[CVPR 2021] Released code for Counterfactual Zero-Shot and Open-Set Visual Recognition

Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention

Pretraining Representations For Data-Efficient Reinforcement Learning

A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing.

Experiments with differentiable stacks and queues in PyTorch

This repo generates the training data and the model for Morpheus-Deblend

a pytorch implementation of auto-punctuation learned character by character

LabelImg is a graphical image annotation tool.

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

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Official implementation of Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter

Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy" (ICLR 2022 Spotlight)

The official implementation of NeurIPS 2021 paper: Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

Session-aware Item-combination Recommendation with Transformer Network

AlphaBot2 Pi Core software for interfacing with the various components.

Implementation of Memory-Efficient Neural Networks with Multi-Level Generation, ICCV 2021

RoIAlign & crop_and_resize for PyTorch

[ICCV 2021 (oral)] Planar Surface Reconstruction from Sparse Views