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

This repository stores the code to reproduce the results published in "TiWS-iForest: Isolation Forest in Weakly Supervised and Tiny ML scenarios"

Code for testing convergence rates of Lipschitz learning on graphs

A new video text spotting framework with Transformer

Few-shot Learning of GPT-3

RL-driven agent playing tic-tac-toe on starknet against challengers.

All the code and files related to the MI-Lab of UE19CS305 course in sem 5

Image-retrieval-baseline - MUGE Multimodal Retrieval Baseline

This is an example of a reproducible modelling project

Unofficial keras(tensorflow) implementation of MAE model from Masked Autoencoders Are Scalable Vision Learners

💃 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena

Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

CryptoFrog - My First Strategy for freqtrade

Code for SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations

Fully Convolutional DenseNets for semantic segmentation.

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

PyTorch framework for Deep Learning research and development.

"3D Human Texture Estimation from a Single Image with Transformers", ICCV 2021

Distance-Ratio-Based Formulation for Metric Learning

Global-Local Context Network for Person Search