A fast Text-to-Speech (TTS) model. Work well for English, Mandarin/Chinese, Japanese, Korean, Russian and Tibetan (so far). 快速语音合成模型,适用于英语、普通话/中文、日语、韩语、俄语和藏语(当前已测试)。

Overview

简体中文 | English

并行语音合成

[TOC]

新进展

目录结构

.
|--- config/      # 配置文件
     |--- default.yaml
     |--- ...
|--- datasets/    # 数据处理
|--- encoder/     # 声纹编码器
     |--- voice_encoder.py
     |--- ...
|--- helpers/     # 一些辅助类
     |--- trainer.py
     |--- synthesizer.py
     |--- ...
|--- logdir/      # 训练过程保存目录
|--- losses/      # 一些损失函数
|--- models/      # 合成模型
     |--- layers.py
     |--- duration.py
     |--- parallel.py
|--- pretrained/  # 预训练模型(LJSpeech 数据集)
|--- samples/     # 合成样例
|--- utils/       # 一些通用方法
|--- vocoder/     # 声码器
     |--- melgan.py
     |--- ...
|--- wandb/       # Wandb 保存目录
|--- extract-duration.py
|--- extract-embedding.py
|--- LICENSE
|--- prepare-dataset.py  # 准备脚本
|--- README.md
|--- README_en.md
|--- requirements.txt    # 依赖文件
|--- synthesize.py       # 合成脚本
|--- train-duration.py   # 训练脚本
|--- train-parallel.py

合成样例

部分合成样例见这里

预训练

部分预训练模型见这里

快速开始

步骤(1):克隆仓库

$ git clone https://github.com/atomicoo/ParallelTTS.git

步骤(2):安装依赖

$ conda create -n ParallelTTS python=3.7.9
$ conda activate ParallelTTS
$ pip install -r requirements.txt

步骤(3):合成语音

$ python synthesize.py \
  --checkpoint ./pretrained/ljspeech-parallel-epoch0100.pth \
  --melgan_checkpoint ./pretrained/ljspeech-melgan-epoch3200.pth \
  --input_texts ./samples/english/synthesize.txt \
  --outputs_dir ./outputs/

如果要合成其他语种的语音,需要通过 --config 指定相应的配置文件。

如何训练

步骤(1):准备数据

$ python prepare-dataset.py

通过 --config 可以指定配置文件,默认的 default.yaml 针对 LJSpeech 数据集。

步骤(2):训练对齐模型

$ python train-duration.py

步骤(3):提取持续时间

$ python extract-duration.py

通过 --ground_truth 可以指定是否利用对齐模型生成 Ground-Truth 声谱图。

步骤(4):训练合成模型

$ python train-parallel.py

通过 --ground_truth 可以指定是否使用 Ground-Truth 声谱图进行模型训练。

训练日志

如果使用 TensorBoardX,则运行如下命令:

$ tensorboard --logdir logdir/[DIR]/

强烈推荐使用 Wandb(Weights & Biases),只需在上述训练命令中增加 --enable_wandb 选项。

数据集

  • LJSpeech:英语,女性,22050 Hz,约 24 小时
  • LibriSpeech:英语,多说话人(仅使用 train-clean-100 部分),16000 Hz,总计约 1000 小时
  • JSUT:日语,女性,48000 Hz,约 10 小时
  • BiaoBei:普通话,女性,48000 Hz,约 12 小时
  • KSS:韩语,女性,44100 Hz,约 12 小时
  • RuLS:俄语,多说话人(仅使用单一说话人音频),16000 Hz,总计约 98 小时
  • TWLSpeech(非公开,质量较差):藏语,女性(多说话人,音色相近),16000 Hz,约 23 小时

质量评估

TODO:待补充

速度指标

训练速度:对于 LJSpeech 数据集,设置批次尺寸为 64,可以在单张 8GB 显存的 GTX 1080 显卡上进行训练,训练 ~8h(~300 epochs)后即可合成质量较高的语音。

合成速度:以下测试在 CPU @ Intel Core i7-8550U / GPU @ NVIDIA GeForce MX150 下进行,每段合成音频在 8 秒左右(约 20 词)

批次尺寸 Spec
(GPU)
Audio
(GPU)
Spec
(CPU)
Audio
(CPU)
1 0.042 0.218 0.100 2.004
2 0.046 0.453 0.209 3.922
4 0.053 0.863 0.407 7.897
8 0.062 2.386 0.878 14.599

注意,没有进行多次测试取平均值,结果仅供参考。

一些问题

  • wavegan 分支中,vocoder 代码取自 ParallelWaveGAN,由于声学特征提取方式不兼容,需要进行转化,具体转化代码见这里
  • 普通话模型的文本输入选择拼音序列,因为 BiaoBei 的原始拼音序列不包含标点、以及对齐模型训练不完全,所以合成语音的节奏会有点问题。
  • 韩语模型没有专门训练对应的声码器,而是直接使用 LJSpeech(同为 22050 Hz)的声码器,可能稍微影响合成语音的质量。

参考资料

TODO

  • 合成语音质量评估(MOS)
  • 更多不同语种的测试
  • 语音风格迁移(音色)

欢迎交流

  • 微信号:Joee1995

  • 企鹅号:793071559

Owner
Atomicoo
Atomicoo
PyTorch Implementation of "Non-Autoregressive Neural Machine Translation"

Non-Autoregressive Transformer Code release for Non-Autoregressive Neural Machine Translation by Jiatao Gu, James Bradbury, Caiming Xiong, Victor O.K.

Salesforce 261 Nov 12, 2022
Implemented shortest-circuit disambiguation, maximum probability disambiguation, HMM-based lexical annotation and BiLSTM+CRF-based named entity recognition

Implemented shortest-circuit disambiguation, maximum probability disambiguation, HMM-based lexical annotation and BiLSTM+CRF-based named entity recognition

0 Feb 13, 2022
YACLC - Yet Another Chinese Learner Corpus

汉语学习者文本多维标注数据集YACLC V1.0 中文 | English 汉语学习者文本多维标注数据集(Yet Another Chinese Learner

BLCU-ICALL 47 Dec 15, 2022
This repository contains helper functions which can help you generate additional data points depending on your NLP task.

NLP Albumentations For Data Augmentation This repository contains helper functions which can help you generate additional data points depending on you

Aflah 6 May 22, 2022
State of the Art Natural Language Processing

Spark NLP: State of the Art Natural Language Processing Spark NLP is a Natural Language Processing library built on top of Apache Spark ML. It provide

John Snow Labs 3k Jan 05, 2023
A very simple framework for state-of-the-art Natural Language Processing (NLP)

A very simple framework for state-of-the-art NLP. Developed by Humboldt University of Berlin and friends. IMPORTANT: (30.08.2020) We moved our models

flair 12.3k Dec 31, 2022
Code for our paper "Transfer Learning for Sequence Generation: from Single-source to Multi-source" in ACL 2021.

TRICE: a task-agnostic transferring framework for multi-source sequence generation This is the source code of our work Transfer Learning for Sequence

THUNLP-MT 9 Jun 27, 2022
Precision Medicine Knowledge Graph (PrimeKG)

PrimeKG Website | bioRxiv Paper | Harvard Dataverse Precision Medicine Knowledge Graph (PrimeKG) presents a holistic view of diseases. PrimeKG integra

Machine Learning for Medicine and Science @ Harvard 103 Dec 10, 2022
Understand Text Summarization and create your own summarizer in python

Automatic summarization is the process of shortening a text document with software, in order to create a summary with the major points of the original document. Technologies that can make a coherent

Sreekanth M 1 Oct 18, 2022
Implementation of some unbalanced loss like focal_loss, dice_loss, DSC Loss, GHM Loss et.al

Implementation of some unbalanced loss for NLP task like focal_loss, dice_loss, DSC Loss, GHM Loss et.al Summary Here is a loss implementation reposit

121 Jan 01, 2023
This is an incredibly powerful calculator that is capable of many useful day-to-day functions.

Description 💻 This is an incredibly powerful calculator that is capable of many useful day-to-day functions. Such functions include solving basic ari

Jordan Leich 37 Nov 19, 2022
PyWorld3 is a Python implementation of the World3 model

The World3 model revisited in Python Install & Hello World3 How to tune your own simulation Licence How to cite PyWorld3 with Bibtex References & ackn

Charles Vanwynsberghe 248 Dec 14, 2022
Simple and efficient RevNet-Library with DeepSpeed support

RevLib Simple and efficient RevNet-Library with DeepSpeed support Features Half the constant memory usage and faster than RevNet libraries Less memory

Lucas Nestler 112 Dec 05, 2022
Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge This is an implementation of the paper,

Mutian He 19 Oct 14, 2022
A framework for implementing federated learning

This is partly the reproduction of the paper of [Privacy-Preserving Federated Learning in Fog Computing](DOI: 10.1109/JIOT.2020.2987958. 2020)

DavidChen 46 Sep 23, 2022
中文生成式预训练模型

T5 PEGASUS 中文生成式预训练模型,以mT5为基础架构和初始权重,通过类似PEGASUS的方式进行预训练。 详情可见:https://kexue.fm/archives/8209 Tokenizer 我们将T5 PEGASUS的Tokenizer换成了BERT的Tokenizer,它对中文更

410 Jan 03, 2023
Code for the paper: Sequence-to-Sequence Learning with Latent Neural Grammars

Code for the paper: Sequence-to-Sequence Learning with Latent Neural Grammars

Yoon Kim 43 Dec 23, 2022
Türkçe küfürlü içerikleri bulan bir yapay zeka kütüphanesi / An ML library for profanity detection in Turkish sentences

"Kötü söz sahibine aittir." -Anonim Nedir? sinkaf uygunsuz yorumların bulunmasını sağlayan bir python kütüphanesidir. Farkı nedir? Diğer algoritmalard

KaraGoz 4 Feb 18, 2022
MHtyper is an end-to-end pipeline for recognized the Forensic microhaplotypes in Nanopore sequencing data.

MHtyper is an end-to-end pipeline for recognized the Forensic microhaplotypes in Nanopore sequencing data. It is implemented using Python.

willow 6 Jun 27, 2022