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
Python package for performing Entity and Text Matching using Deep Learning.

DeepMatcher DeepMatcher is a Python package for performing entity and text matching using deep learning. It provides built-in neural networks and util

461 Dec 28, 2022
Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms

FNet: Mixing Tokens with Fourier Transforms Pytorch implementation of Fnet : Mixing Tokens with Fourier Transforms. Citation: @misc{leethorp2021fnet,

Rishikesh (ऋषिकेश) 217 Dec 05, 2022
Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields

Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields [project page][paper][cite] Geometry-Consistent Neural Shape Represe

Yifan Wang 100 Dec 19, 2022
Healthsea is a spaCy pipeline for analyzing user reviews of supplementary products for their effects on health.

Welcome to Healthsea ✨ Create better access to health with spaCy. Healthsea is a pipeline for analyzing user reviews to supplement products by extract

Explosion 75 Dec 19, 2022
🚀 RocketQA, dense retrieval for information retrieval and question answering, including both Chinese and English state-of-the-art models.

In recent years, the dense retrievers based on pre-trained language models have achieved remarkable progress. To facilitate more developers using cutt

475 Jan 04, 2023
A flask application to predict the speech emotion of any .wav file.

This is a speech emotion recognition app. It will allow you to train a modular MLP model with the RAVDESS dataset, and then use that model with a flask application to predict the speech emotion of an

Aryan Vijaywargia 2 Dec 15, 2021
Multi Task Vision and Language

12-in-1: Multi-Task Vision and Language Representation Learning Please cite the following if you use this code. Code and pre-trained models for 12-in-

Meta Research 711 Jan 08, 2023
Converts text into a PDF of handwritten notes

Text To Handwritten Notes Converts text into a PDF of handwritten notes Explore the docs » · Report Bug · Request Feature · Steps: $ git clone https:/

UVSinghK 63 Oct 09, 2022
CCF BDCI 2020 房产行业聊天问答匹配赛道 A榜47/2985

CCF BDCI 2020 房产行业聊天问答匹配 A榜47/2985 赛题描述详见:https://www.datafountain.cn/competitions/474 文件说明 data: 存放训练数据和测试数据以及预处理代码 model_bert.py: 网络模型结构定义 adv_train

shuo 40 Sep 28, 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
Exploration of BERT-based models on twitter sentiment classifications

twitter-sentiment-analysis Explore the relationship between twitter sentiment of Tesla and its stock price/return. Explore the effect of different BER

Sammy Cui 2 Oct 02, 2022
This is a general repo that helps you develop fast/effective NLP classifiers using Huggingface

NLP Classifier Introduction This project trains a bert model on any NLP classifcation model. And uses the model in make predictions on new data using

Abdullah Tarek 3 Mar 11, 2022
Web Scraping, Document Deduplication & GPT-2 Fine-tuning with a newly created scam dataset.

Web Scraping, Document Deduplication & GPT-2 Fine-tuning with a newly created scam dataset.

18 Nov 28, 2022
PUA Programming Language written in Python.

pua-lang PUA Programming Language written in Python. Installation git clone https://github.com/zhaoyang97/pua-lang.git cd pua-lang pip install . Try

zy 4 Feb 19, 2022
This repository has a implementations of data augmentation for NLP for Japanese.

daaja This repository has a implementations of data augmentation for NLP for Japanese: EDA: Easy Data Augmentation Techniques for Boosting Performance

Koga Kobayashi 60 Nov 11, 2022
ProteinBERT is a universal protein language model pretrained on ~106M proteins from the UniRef90 dataset.

ProteinBERT is a universal protein language model pretrained on ~106M proteins from the UniRef90 dataset. Through its Python API, the pretrained model can be fine-tuned on any protein-related task in

241 Jan 04, 2023
Club chatbot

Chatbot Club chatbot Instructions to get the Chatterbot working Step 1. First make sure you are using a version of Python 3 or newer. To check your ve

5 Mar 07, 2022
A Japanese tokenizer based on recurrent neural networks

Nagisa is a python module for Japanese word segmentation/POS-tagging. It is designed to be a simple and easy-to-use tool. This tool has the following

325 Jan 05, 2023
Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

Espresso Espresso is an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning libra

Yiming Wang 919 Jan 03, 2023
Simple Annotated implementation of GPT-NeoX in PyTorch

Simple Annotated implementation of GPT-NeoX in PyTorch This is a simpler implementation of GPT-NeoX in PyTorch. We have taken out several optimization

labml.ai 101 Dec 03, 2022