# tacotron_pytorch
[![Build Status](https://travis-ci.org/r9y9/tacotron_pytorch.svg?branch=master)](https://travis-ci.org/r9y9/tacotron_pytorch)
PyTorch implementation of [Tacotron](https://arxiv.org/abs/1703.10135) speech synthesis model.
Inspired from [keithito/tacotron](https://github.com/keithito/tacotron). Currently not as much good speech quality as [keithito/tacotron](https://github.com/keithito/tacotron) can generate, but it seems to be basically working. You can find some generated speech examples trained on [LJ Speech Dataset](https://keithito.com/LJ-Speech-Dataset/) at [here](http://nbviewer.jupyter.org/github/r9y9/tacotron_pytorch/blob/master/notebooks/Test%20Tacotron.ipynb).
If you are comfortable working with TensorFlow, I'd recommend you to try
https://github.com/keithito/tacotron instead. The reason to rewrite it in PyTorch is that it's easier to debug and extend (multi-speaker architecture, etc) at least to me.
## Requirements
- PyTorch
- TensorFlow (if you want to run the training script. This definitely can be optional, but for now required.)
## Installation
```
git clone --recursive https://github.com/r9y9/tacotron_pytorch
pip install -e . # or python setup.py develop
```
If you want to run the training script, then you need to install additional dependencies.
```
pip install -e ".[train]"
```
## Training
The package relis on [keithito/tacotron](https://github.com/keithito/tacotron) for text processing, audio preprocessing and audio reconstruction (added as a submodule). Please follows the quick start section at https://github.com/keithito/tacotron and prepare your dataset accordingly.
If you have your data prepared, assuming your data is in `"~/tacotron/training"` (which is the default), then you can train your model by:
```
python train.py
```
Alignment, predicted spectrogram, target spectrogram, predicted waveform and checkpoint (model and optimizer states) are saved per 1000 global step in `checkpoints` directory. Training progress can be monitored by:
```
tensorboard --logdir=log
```
## Testing model
Open the notebook in `notebooks` directory and change `checkpoint_path` to your model.
没有合适的资源?快使用搜索试试~ 我知道了~
Python-PyTorch实现了Tacotron语音合成模型
共16个文件
py:9个
yml:2个
md:2个
2星 需积分: 48 20 下载量 114 浏览量
2019-08-11
04:08:36
上传
评论 4
收藏 11.47MB ZIP 举报
温馨提示
PyTorch实现了Tacotron语音合成模型
资源推荐
资源详情
资源评论
收起资源包目录
Python-PyTorch实现了Tacotron语音合成模型.zip (16个子文件)
tacotron_pytorch-master
.travis.yml 959B
.gitmodules 88B
tacotron_pytorch
attention.py 3KB
tacotron.py 11KB
__init__.py 152B
synthesis.py 3KB
.github
stale.yml 1KB
train.py 12KB
tests
test_tacotron.py 1KB
test_attention.py 1KB
hparams.py 1KB
setup.py 2KB
LICENSE.md 1KB
.gitignore 2KB
lib
tacotron
README.md 2KB
notebooks
Test Tacotron.ipynb 16.75MB
共 16 条
- 1
资源评论
- sirius·月2021-04-15没有训练好的模型吗
weixin_39841882
- 粉丝: 443
- 资源: 1万+
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功