Pytorch Implementation of DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis (TTS Extension)

Overview

DiffSinger - PyTorch Implementation

PyTorch implementation of DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis (TTS Extension).

Status (2021.06.03)

  • Naive Version of DiffSinger
  • Shallow Diffusion Mechanism: Training boundary predictor by leveraging pre-trained auxiliary decoder + Training denoiser using k as a maximum time step

Quickstart

Dependencies

You can install the Python dependencies with

pip3 install -r requirements.txt

Inference

You have to download the pretrained models and put them in output/ckpt/LJSpeech/.

For English single-speaker TTS, run

python3 synthesize.py --text "YOUR_DESIRED_TEXT" --restore_step 160000 --mode single -p config/LJSpeech/preprocess.yaml -m config/LJSpeech/model.yaml -t config/LJSpeech/train.yaml

The generated utterances will be put in output/result/.

Batch Inference

Batch inference is also supported, try

python3 synthesize.py --source preprocessed_data/LJSpeech/val.txt --restore_step 160000 --mode batch -p config/LJSpeech/preprocess.yaml -m config/LJSpeech/model.yaml -t config/LJSpeech/train.yaml

to synthesize all utterances in preprocessed_data/LJSpeech/val.txt

Controllability

The pitch/volume/speaking rate of the synthesized utterances can be controlled by specifying the desired pitch/energy/duration ratios. For example, one can increase the speaking rate by 20 % and decrease the volume by 20 % by

python3 synthesize.py --text "YOUR_DESIRED_TEXT" --restore_step 160000 --mode single -p config/LJSpeech/preprocess.yaml -m config/LJSpeech/model.yaml -t config/LJSpeech/train.yaml --duration_control 0.8 --energy_control 0.8

Training

Datasets

The supported datasets are

  • LJSpeech: a single-speaker English dataset consists of 13100 short audio clips of a female speaker reading passages from 7 non-fiction books, approximately 24 hours in total.
  • (will be added more)

Preprocessing

First, run

python3 prepare_align.py config/LJSpeech/preprocess.yaml

for some preparations.

As described in the paper, Montreal Forced Aligner (MFA) is used to obtain the alignments between the utterances and the phoneme sequences. Alignments for the LJSpeech datasets are provided here from ming024's FastSpeech2. You have to unzip the files in preprocessed_data/LJSpeech/TextGrid/.

After that, run the preprocessing script by

python3 preprocess.py config/LJSpeech/preprocess.yaml

Alternately, you can align the corpus by yourself. Download the official MFA package and run

./montreal-forced-aligner/bin/mfa_align raw_data/LJSpeech/ lexicon/librispeech-lexicon.txt english preprocessed_data/LJSpeech

or

./montreal-forced-aligner/bin/mfa_train_and_align raw_data/LJSpeech/ lexicon/librispeech-lexicon.txt preprocessed_data/LJSpeech

to align the corpus and then run the preprocessing script.

python3 preprocess.py config/LJSpeech/preprocess.yaml

Training

Train your model with

python3 train.py -p config/LJSpeech/preprocess.yaml -m config/LJSpeech/model.yaml -t config/LJSpeech/train.yaml

TensorBoard

Use

tensorboard --logdir output/log/LJSpeech

to serve TensorBoard on your localhost. The loss curves, synthesized mel-spectrograms, and audios are shown.

Implementation Issues

  1. Pitch extractor comparison (on LJ001-0006.wav)

    pyworld is used to extract f0 (fundamental frequency) as pitch information in this implementation. Empirically, however, I found that all three methods were equally acceptable for clean datasets (e.g., LJSpeech) as above figures. Note that pysptk would work better for noisy datasets (as described in STYLER).

  2. Stack two layers of FFTBlock for the lyrics encoder (text encoder).

  3. (Naive version) The number of learnable parameters is 34.337M, which is larger than the original paper (26.744M). The diffusion module takes a significant portion of whole parameters.

  4. I did not remove the energy prediction of FastSpeech2 since it is not critical to the model training or performance (as described in LightSpeech). It should be easily removed without any performance degradation.

  5. Use HiFi-GAN instead of Parallel WaveGAN (PWG) for vocoding.

Citation

@misc{lee2021diffsinger,
  author = {Lee, Keon},
  title = {DiffSinger},
  year = {2021},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/keonlee9420/DiffSinger}}
}

References

You might also like...
This is the implementation of "SELF SUPERVISED REPRESENTATION LEARNING WITH DEEP CLUSTERING FOR ACOUSTIC UNIT DISCOVERY FROM RAW SPEECH" submitted to ICASSP 2022

CPC_DeepCluster This is the implementation of "SELF SUPERVISED REPRESENTATION LEARNING WITH DEEP CLUSTERING FOR ACOUSTIC UNIT DISCOVERY FROM RAW SPEEC

Pytorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Pytorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling

Parallel Tacotron2 Pytorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling

PyTorch implementation of the method described in the paper VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop.
PyTorch implementation of the method described in the paper VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop.

VoiceLoop PyTorch implementation of the method described in the paper VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop. VoiceLoop is a n

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

Codebase for Diffusion Models Beat GANS on Image Synthesis.

Codebase for Diffusion Models Beat GANS on Image Synthesis.

High-Resolution Image Synthesis with Latent Diffusion Models
High-Resolution Image Synthesis with Latent Diffusion Models

Latent Diffusion Models Requirements A suitable conda environment named ldm can be created and activated with: conda env create -f environment.yaml co

BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

Bilateral Denoising Diffusion Models (BDDMs) This is the official PyTorch implementation of the following paper: BDDM: BILATERAL DENOISING DIFFUSION M

Code release for paper: The Boombox: Visual Reconstruction from Acoustic Vibrations
Code release for paper: The Boombox: Visual Reconstruction from Acoustic Vibrations

The Boombox: Visual Reconstruction from Acoustic Vibrations Boyuan Chen, Mia Chiquier, Hod Lipson, Carl Vondrick Columbia University Project Website |

Multistream CNN for Robust Acoustic Modeling
Multistream CNN for Robust Acoustic Modeling

Multistream Convolutional Neural Network (CNN) A multistream CNN is a novel neural network architecture for robust acoustic modeling in speech recogni

Comments
  • Training Error

    Training Error

    In this case, , i ran the scripts python3 train.py -p config/vietnam/preprocess.yaml -m config/vietnam/model.yaml -t config/vietnam/train.yaml File "train.py", line 199, in main(args, configs) File "train.py", line 85, in main losses = Loss(batch, output) File "/home/thanhdo/envs/diffsinger_env/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/thanhdo/Documents/DiffSinger/model/loss.py", line 69, in forward log_duration_targets = log_duration_targets.masked_select(src_masks) RuntimeError: The size of tensor a (39) must match the size of tensor b (136) at non-singleton dimension 1

    Screen Shot 2021-06-23 at 3 56 10 PM

    opened by thanhdo99 8
  • diffusion_projection in ResidualBlock

    diffusion_projection in ResidualBlock

    Your implementation has diffusion_projection for every residual block similar to DiffWave, but this is inconsistent with the paper as the original architecture directly adds E_t (output of the step embedding module) to the input before the first convolution layer. Is there a reason behind this change?

    opened by tebin 1
Releases(v0.1.0)
Owner
Keon Lee
Conversational AI | Expressive Speech Synthesis | Open-domain Dialog | Empathic Computing | NLP | Disentangled Representation | Generative Models | HCI
Keon Lee
Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision (ICCV 2021)

Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision (ICCV 2021) PyTorch implementation of Learning RAW-to-sRGB Mappings with Inaccurat

Zhilu Zhang 53 Dec 20, 2022
Implementation of Vaswani, Ashish, et al. "Attention is all you need."

Attention Is All You Need Paper Implementation This is my from-scratch implementation of the original transformer architecture from the following pape

Brando Koch 195 Dec 30, 2022
For medical image segmentation

LeViT_UNet For medical image segmentation Our model is based on LeViT (https://github.com/facebookresearch/LeViT). You'd better gitclone its codes. Th

13 Dec 24, 2022
The official PyTorch implementation for the paper "sMGC: A Complex-Valued Graph Convolutional Network via Magnetic Laplacian for Directed Graphs".

Magnetic Graph Convolutional Networks About The official PyTorch implementation for the paper sMGC: A Complex-Valued Graph Convolutional Network via M

3 Feb 25, 2022
Image Super-Resolution Using Very Deep Residual Channel Attention Networks

Image Super-Resolution Using Very Deep Residual Channel Attention Networks

kongdebug 14 Oct 14, 2022
Fast and accurate optimisation for registration with little learningconvexadam

convexAdam Learn2Reg 2021 Submission Fast and accurate optimisation for registration with little learning Excellent results on Learn2Reg 2021 challeng

17 Dec 06, 2022
SoGCN: Second-Order Graph Convolutional Networks

SoGCN: Second-Order Graph Convolutional Networks This is the authors' implementation of paper "SoGCN: Second-Order Graph Convolutional Networks" in Py

Yuehao 7 Aug 16, 2022
Training and Evaluation Code for Neural Volumes

Neural Volumes This repository contains training and evaluation code for the paper Neural Volumes. The method learns a 3D volumetric representation of

Meta Research 370 Dec 08, 2022
A toolset of Python programs for signal modeling and indentification via sparse semilinear autoregressors.

SPAAR Description A toolset of Python programs for signal modeling via sparse semilinear autoregressors. References Vides, F. (2021). Computing Semili

Fredy Vides 0 Oct 30, 2021
Phy-Q: A Benchmark for Physical Reasoning

Phy-Q: A Benchmark for Physical Reasoning Cheng Xue*, Vimukthini Pinto*, Chathura Gamage* Ekaterina Nikonova, Peng Zhang, Jochen Renz School of Comput

29 Dec 19, 2022
SAS output to EXCEL converter for Cornell/MIT Language and acquisition lab

CORNELLSASLAB SAS output to EXCEL converter for Cornell/MIT Language and acquisition lab Instructions: This python code can be used to convert SAS out

2 Jan 26, 2022
Hierarchical Memory Matching Network for Video Object Segmentation (ICCV 2021)

Hierarchical Memory Matching Network for Video Object Segmentation Hongje Seong, Seoung Wug Oh, Joon-Young Lee, Seongwon Lee, Suhyeon Lee, Euntai Kim

Hongje Seong 72 Dec 14, 2022
DTCN IJCAI - Sequential prediction learning framework and algorithm

DTCN This is the implementation of our paper "Sequential Prediction of Social Me

Bobby 2 Jan 24, 2022
Unsupervised captioning - Code for Unsupervised Image Captioning

Unsupervised Image Captioning by Yang Feng, Lin Ma, Wei Liu, and Jiebo Luo Introduction Most image captioning models are trained using paired image-se

Yang Feng 207 Dec 24, 2022
Text Summarization - WCN — Weighted Contextual N-gram method for evaluation of Text Summarization

Text Summarization WCN — Weighted Contextual N-gram method for evaluation of Text Summarization In this project, I fine tune T5 model on Extreme Summa

Aditya Shah 1 Jan 03, 2022
Deep Learning Specialization by Andrew Ng, deeplearning.ai.

Deep Learning Specialization on Coursera Master Deep Learning, and Break into AI This is my personal projects for the course. The course covers deep l

Engen 1.5k Jan 07, 2023
Repository of the paper Compressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative Models at ML4AD @ NeurIPS 2021.

Compressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative Models Code and supplementary materials Repository of the p

Daniel Bogdoll 4 Jul 13, 2022
[NeurIPS 2021] The PyTorch implementation of paper "Self-Supervised Learning Disentangled Group Representation as Feature"

IP-IRM [NeurIPS 2021] The PyTorch implementation of paper "Self-Supervised Learning Disentangled Group Representation as Feature". Codes will be relea

Wang Tan 67 Dec 24, 2022
WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose

WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose Yijun Zhou and James Gregson - BMVC2020 Abstract: We present an end-to-end head-pos

368 Dec 26, 2022
Optimal space decomposition based-product quantization for approximate nearest neighbor search

Optimal space decomposition based-product quantization for approximate nearest neighbor search Abstract Product quantization(PQ) is an effective neare

Mylove 1 Nov 19, 2021