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
Tool to add main subject to items on Wikidata using a WMFs CirrusSearch for named entity recognition or a manually supplied list of QIDs

ItemSubjector Tool made to add main subject statements to items based on the title using a home-brewed CirrusSearch-based Named Entity Recognition alg

Dennis Priskorn 9 Nov 17, 2022
code for modular summarization work published in ACL2021 by Krishna et al

This repository contains the code for running modular summarization pipelines as described in the publication Krishna K, Khosla K, Bigham J, Lipton ZC

Kundan Krishna 6 Jun 04, 2021
Simple, Fast, Powerful and Easily extensible python package for extracting patterns from text, with over than 60 predefined Regular Expressions.

patterns-finder Simple, Fast, Powerful and Easily extensible python package for extracting patterns from text, with over than 60 predefined Regular Ex

22 Dec 19, 2022
ANTLR (ANother Tool for Language Recognition) is a powerful parser generator for reading, processing, executing, or translating structured text or binary files.

ANTLR (ANother Tool for Language Recognition) is a powerful parser generator for reading, processing, executing, or translating structured text or binary files.

Antlr Project 13.6k Jan 05, 2023
Sequence-to-Sequence Framework in PyTorch

nmtpytorch allows training of various end-to-end neural architectures including but not limited to neural machine translation, image captioning and au

LIUM 395 Nov 21, 2022
Easy Language Model Pretraining leveraging Huggingface's Transformers and Datasets

Easy Language Model Pretraining leveraging Huggingface's Transformers and Datasets What is LASSL • How to Use What is LASSL LASSL은 LAnguage Semi-Super

LASSL: LAnguage Self-Supervised Learning 116 Dec 27, 2022
Understanding the Difficulty of Training Transformers

Admin Understanding the Difficulty of Training Transformers Guided by our analyses, we propose Adaptive Model Initialization (Admin), which successful

Liyuan Liu 300 Dec 29, 2022
Code for the paper "BERT Loses Patience: Fast and Robust Inference with Early Exit".

Patience-based Early Exit Code for the paper "BERT Loses Patience: Fast and Robust Inference with Early Exit". NEWS: We now have a better and tidier i

Kevin Canwen Xu 54 Jan 04, 2023
AudioCLIP Extending CLIP to Image, Text and Audio

AudioCLIP Extending CLIP to Image, Text and Audio This repository contains implementation of the models described in the paper arXiv:2106.13043. This

458 Jan 02, 2023
The ibet-Prime security token management system for ibet network.

ibet-Prime The ibet-Prime security token management system for ibet network. Features ibet-Prime is an API service that enables the issuance and manag

BOOSTRY 8 Dec 22, 2022
A natural language modeling framework based on PyTorch

Overview PyText is a deep-learning based NLP modeling framework built on PyTorch. PyText addresses the often-conflicting requirements of enabling rapi

Meta Research 6.4k Jan 08, 2023
NLP library designed for reproducible experimentation management

Welcome to the Transfer NLP library, a framework built on top of PyTorch to promote reproducible experimentation and Transfer Learning in NLP You can

Feedly 290 Dec 20, 2022
PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

VAENAR-TTS - PyTorch Implementation PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

Keon Lee 67 Nov 14, 2022
Sample data associated with the Aurora-BP study

The Aurora-BP Study and Dataset This repository contains sample code, sample data, and explanatory information for working with the Aurora-BP dataset

Microsoft 16 Dec 12, 2022
Optimal Transport Tools (OTT), A toolbox for all things Wasserstein.

Optimal Transport Tools (OTT), A toolbox for all things Wasserstein. See full documentation for detailed info on the toolbox. The goal of OTT is to pr

OTT-JAX 255 Dec 26, 2022
Deduplication is the task to combine different representations of the same real world entity.

Deduplication is the task to combine different representations of the same real world entity. This package implements deduplication using active learning. Active learning allows for rapid training wi

63 Nov 17, 2022
Implementation of TTS with combination of Tacotron2 and HiFi-GAN

Tacotron2-HiFiGAN-master Implementation of TTS with combination of Tacotron2 and HiFi-GAN for Mandarin TTS. Inference In order to inference, we need t

SunLu Z 7 Nov 11, 2022
Transformer training code for sequential tasks

Sequential Transformer This is a code for training Transformers on sequential tasks such as language modeling. Unlike the original Transformer archite

Meta Research 578 Dec 13, 2022
Production First and Production Ready End-to-End Keyword Spotting Toolkit

Production First and Production Ready End-to-End Keyword Spotting Toolkit

223 Jan 02, 2023
Repository for fine-tuning Transformers 🤗 based seq2seq speech models in JAX/Flax.

Seq2Seq Speech in JAX A JAX/Flax repository for combining a pre-trained speech encoder model (e.g. Wav2Vec2, HuBERT, WavLM) with a pre-trained text de

Sanchit Gandhi 21 Dec 14, 2022