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

Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition

Official Implementation of "Transformers Can Do Bayesian Inference"

Measures input lag without dedicated hardware, performing motion detection on recorded or live video

Predicting Student Attentiveness using OpenCV

PyTorch implementation of "Optimization Planning for 3D ConvNets"

MCMC samplers for Bayesian estimation in Python, including Metropolis-Hastings, NUTS, and Slice

ICCV2021 - Mining Contextual Information Beyond Image for Semantic Segmentation

A motion tracking system for any arbitaray points in a video frame.

Mixed Neural Likelihood Estimation for models of decision-making

ONNX Command-Line Toolbox

Code for the upcoming CVPR 2021 paper

Resources related to EMNLP 2021 paper "FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations"

Compute FID scores with PyTorch.

[PNAS2021] The neural architecture of language: Integrative modeling converges on predictive processing

DenseNet Implementation in Keras with ImageNet Pretrained Models

LegoDNN: a block-grained scaling tool for mobile vision systems

Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]

This repository is an implementation of paper : Improving the Training of Graph Neural Networks with Consistency Regularization

A code implementation of AC-GC: Activation Compression with Guaranteed Convergence, in NeurIPS 2021.

Tensorflow implementation of ID-Unet: Iterative Soft and Hard Deformation for View Synthesis.