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

A tool to visualise the results of AlphaFold2 and inspect the quality of structural predictions

Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style"

Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. In CVPR 2022.

Studying Python release adoptions by looking at PyPI downloads

Manifold-Mixup implementation for fastai V2

Code for Efficient Visual Pretraining with Contrastive Detection

🏅 Top 5% in 제2회 연구개발특구 인공지능 경진대회 AI SPARK 챌린지

Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation

Code for our work "Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection".

Deep Learning Based Fasion Recommendation System for Ecommerce

A Context-aware Visual Attention-based training pipeline for Object Detection from a Webpage screenshot!

The pytorch implementation of SOKD (BMVC2021).

An open-source project for applying deep learning to medical scenarios

HyperaPy: An automatic hyperparameter optimization framework ⚡🚀

Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track (SIGIR 2021 Full Paper).

Speech recognition tool to convert audio to text transcripts, for Linux and Raspberry Pi.

Transformer in Computer Vision

This is an implementation of Googles Yogi-Optimizer in Keras (tf.keras)

(SIGIR2020) “Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback’’

PixelPyramids: Exact Inference Models from Lossless Image Pyramids (ICCV 2021)