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
Code for hyperboloid embeddings for knowledge graph entities

Implementation for the papers: Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs, Nurendra Choudhary, Nikhil Rao,

30 Dec 10, 2022
Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention

Sinkhorn Transformer This is a reproduction of the work outlined in Sparse Sinkhorn Attention, with additional enhancements. It includes a parameteriz

Phil Wang 217 Nov 25, 2022
The SVO-Probes Dataset for Verb Understanding

The SVO-Probes Dataset for Verb Understanding This repository contains the SVO-Probes benchmark designed to probe for Subject, Verb, and Object unders

DeepMind 20 Nov 30, 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
A look-ahead multi-entity Transformer for modeling coordinated agents.

baller2vec++ This is the repository for the paper: Michael A. Alcorn and Anh Nguyen. baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling

Michael A. Alcorn 30 Dec 16, 2022
Knowledge Oriented Programming Language

KoPL: 面向知识的推理问答编程语言 安装 | 快速开始 | 文档 KoPL全称 Knowledge oriented Programing Language, 是一个为复杂推理问答而设计的编程语言。我们可以将自然语言问题表示为由基本函数组合而成的KoPL程序,程序运行的结果就是问题的答案。目前,

THU-KEG 62 Dec 12, 2022
Simple Speech to Text, Text to Speech

Simple Speech to Text, Text to Speech 1. Download Repository Opsi 1 Download repository ini, extract di lokasi yang diinginkan Opsi 2 Jika sudah famil

Habib Abdurrasyid 5 Dec 28, 2021
An open source framework for seq2seq models in PyTorch.

pytorch-seq2seq Documentation This is a framework for sequence-to-sequence (seq2seq) models implemented in PyTorch. The framework has modularized and

International Business Machines 1.4k Jan 02, 2023
Guide: Finetune GPT2-XL (1.5 Billion Parameters) and GPT-NEO (2.7 B) on a single 16 GB VRAM V100 Google Cloud instance with Huggingface Transformers using DeepSpeed

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and GPT-NEO (2.7 Billion Parameters) on a single 16 GB VRAM V100 Google Cloud instance with Huggingfa

289 Jan 06, 2023
Opal-lang - A WIP programming language based on Python

thanks to aphitorite for the beautiful logo! opal opal is a WIP transcompiled pr

3 Nov 04, 2022
Word2Wave: a framework for generating short audio samples from a text prompt using WaveGAN and COALA.

Word2Wave is a simple method for text-controlled GAN audio generation. You can either follow the setup instructions below and use the source code and CLI provided in this repo or you can have a play

Ilaria Manco 91 Dec 23, 2022
German Text-To-Speech Engine using Tacotron and Griffin-Lim

jotts JoTTS is a German text-to-speech engine using tacotron and griffin-lim. The synthesizer model has been trained on my voice using Tacotron1. Due

padmalcom 6 Aug 28, 2022
The Easy-to-use Dialogue Response Selection Toolkit for Researchers

The Easy-to-use Dialogue Response Selection Toolkit for Researchers

GMFTBY 32 Nov 13, 2022
InferSent sentence embeddings

InferSent InferSent is a sentence embeddings method that provides semantic representations for English sentences. It is trained on natural language in

Facebook Research 2.2k Dec 27, 2022
Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.

Summarization, translation, Q&A, text generation and more at blazing speed using a T5 version implemented in ONNX. This package is still in alpha stag

Abel 211 Dec 28, 2022
Python port of Google's libphonenumber

phonenumbers Python Library This is a Python port of Google's libphonenumber library It supports Python 2.5-2.7 and Python 3.x (in the same codebase,

David Drysdale 3.1k Dec 29, 2022
Community and sentiment analysis based on tweets

The project has set itself the goal of analyzing the thoughts and interaction of Italian users through the social posts expressed through the Twitter platform on the day of the entry into force of th

3 Nov 17, 2022
Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization

Line as a Visual Sentence with LineTR This repository contains the inference code, pretrained model, and demo scripts of the following paper. It suppo

SungHo Yoon 158 Dec 27, 2022
The RWKV Language Model

RWKV-LM We propose the RWKV language model, with alternating time-mix and channel-mix layers: The R, K, V are generated by linear transforms of input,

PENG Bo 877 Jan 05, 2023
VampiresVsWerewolves - Our Implementation of a MiniMax algorithm with alpha beta pruning in the context of an in-class competition

VampiresVsWerewolves Our Implementation of a MiniMax algorithm with alpha beta pruning in the context of an in-class competition. Our Algorithm finish

Shawn 1 Jan 21, 2022