add documentation sections

doc/source/advanced.rst

@@ -0,0 +1,31 @@
+======================
+Advanced Usage
+======================
+
+This sections covers how to extend parakeet by implementing you own models and 
+experiments. Guidelines on implementation are also elaborated.
+
+Model
+-------------
+
+As a common practice with paddlepaddle, models are implemented as subclasse
+of ``paddle.nn.Layer``. More complicated models, it is recommended to split 
+the model into different components.
+
+For a encoder-decoder model, it is natural to split it into the encoder and 
+the decoder. For a model composed of several similar layers, it is natural to 
+extract the sublayer as a seperate layer.
+
+There are two common ways to define a model which consists of several modules.
+
+#. 
+
+
+Data
+-------------
+
+Config
+-------------
+
+Experiment
+--------------

doc/source/conf.py

@@ -48,6 +48,7 @@ extensions = [
     "sphinx_rtd_theme",
     'sphinx.ext.mathjax',
     'numpydoc',
+    'sphinx.ext.autosummary',
 ]
 
 # Add any paths that contain templates here, relative to this directory.
@@ -63,8 +64,10 @@ exclude_patterns = []
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
+
 html_theme = "sphinx_rtd_theme"
 
+
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".

doc/source/design.rst

@@ -0,0 +1,4 @@
+==============================
+Design of Parakeet
+==============================
+

doc/source/index.rst

@@ -3,14 +3,43 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
-Welcome to parakeet's documentation!
+Parakeet 
 ====================================
 
+``parakeet`` is a deep learning based text-to-speech toolkit built upon ``paddlepaddle`` framework. It aims to provide a flexible, efficient and state-of-the-art text-to-speech toolkit for the open-source community. It includes many influential TTS models proposed by `Baidu Research <http://research.baidu.com>`_ and other research groups. 
+
+``parakeet`` mainly consists of components below.
+
+#. Implementation of models and commonly used neural network layers.
+#. Dataset abstraction and common data preprocessing pipelines.
+#. Ready-to-run experiments.
+
 .. toctree::
-   :maxdepth: 2
+    :caption: Getting started
-   :caption: Contents:
+    :maxdepth: 1
 
+    install
+    tutorials
 
+.. toctree::
+    :caption: Design of Parakeet
+    :maxdepth: 1
+    
+    advanced
+    design
+
+.. toctree::
+    :caption: Documentation
+    :maxdepth: 1
+
+    parakeet.audio
+    parakeet.data
+    parakeet.datasets
+    parakeet.frontend
+    parakeet.modules
+    parakeet.models
+    parakeet.training
+    parakeet.utils
 
 Indices and tables
 ==================

doc/source/install.rst

@@ -0,0 +1,85 @@
+=============
+Installation
+=============
+
+
+Install PaddlePaddle
+-------------------
+Parakeet requires PaddlePaddle as its backend. Not that 2.0rc or newer versions
+of paddle is required.
+
+Since paddlepaddle has multiple packages depending on the device (cpu or gpu) 
+and the dependency libraries, it is recommended to install a proper package of 
+paddlepaddle with respect to the device and dependency library versons via 
+pip. 
+
+Installing paddlepaddle with conda or build paddlepaddle from source is also 
+supported. Please refer to `PaddlePaddle installation <https://www.paddlepaddle.org.cn/install/quick/)>`_ for more details.
+
+Example instruction to install paddlepaddle via pip is listed below.
+
+**PaddlePaddle with gpu**
+
+.. code-block:: bash
+
+    python -m pip install paddlepaddle-gpu==2.0.0rc1.post101 -f https://paddlepaddle.org.cn/whl/stable.html
+    python -m pip install paddlepaddle-gpu==2.0.0rc1.post100 -f https://paddlepaddle.org.cn/whl/stable.html
+
+
+**PaddlePaddle with cpu**
+
+.. code-block:: bash
+
+    python -m pip install paddlepaddle==2.0.0rc1 -i https://mirror.baidu.com/pypi/simple
+
+
+Install libsndfile
+-------------------
+
+Experimemts in parakeet often involve audio and spectrum processing, thus 
+``librosa`` and ``soundfile`` are required. ``soundfile`` requires a extra 
+C library ``libsndfile``, which is not always handled by pip.
+
+For windows and mac users, ``libsndfile`` is also installed when Installing
+``soundfile`` via pip, but for linux users, installing ``libsndfile`` via
+system package manager is required. Example commands for popular distributions 
+are listed below.
+
+.. code-block:: 
+
+    # ubuntu, debian
+    sudo apt-get install libsndfile1
+
+    # centos, fedora,
+    sudo yum install libsndfile
+
+    # openSUSE
+    sudo zypper in libsndfile
+
+For any problem with installtion of soundfile, please refer to 
+`SoundFile <https://pypi.org/project/SoundFile>`_.
+
+Insrall Parakeet
+------------------
+
+There are two ways to install parakeet according to the purpose of using it.
+
+#. If you want to run experiments provided by parakeet or add new models and 
+experiments, it is recommended to clone the project from github 
+(`Parakeet <https://github.com/PaddlePaddle/Parakeet>`_), and install it in 
+editable mode.
+
+   .. code-block:: bash
+     
+     git clone https://github.com/PaddlePaddle/Parakeet
+     cd Parakeet
+     pip install -e .
+
+
+#. If you only need to use the models for inference by parakeet, install from
+pypi is recommended。
+
+   .. code-block:: bash
+
+     pip install paddle-parakeet
+

doc/source/tutorials.rst

@@ -0,0 +1,65 @@
+===========
+Tutorials
+===========
+
+Basic Usage
+-------------------
+
+Pretrained models are provided in a archive. Extract it to get a folder like this::
+
+    checkpoint_name/
+    ├──config.yaml
+    └──step-310000.pdparams
+
+The ``config.yaml`` stores the config used to train the model, the ``step-N.pdparams`` is the parameter file, where N is the steps it has been trained.
+
+The example code below shows how to use the models for prediction.
+
+text to spectrogram
+^^^^^^^^^^^^^^^^^^^^^^
+
+The code below show how to use a transformer_tts model. After loading the pretrained model, use ``model.predict(sentence)`` to generate spectrogram (in numpy.ndarray format), which can be further used to synthesize waveflow.
+
+>>> import parakeet
+>>> from parakeet.frontend import English
+>>> from parakeet.models import TransformerTTS
+>>> from pathlib import Path
+>>> import yacs
+
+>>> # load the pretrained model
+>>> frontend = English()
+>>> checkpoint_dir = Path("transformer_tts_pretrained")
+>>> config = yacs.config.CfgNode.load_cfg(str(checkpoint_dir / "config.yaml"))
+>>> checkpoint_path = str(checkpoint_dir / "step-310000")
+>>> model = TransformerTTS.from_pretrained(
+>>>     frontend, config, checkpoint_path)
+>>> model.eval()
+
+>>> # text to spectrogram
+>>> sentence = "Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition"
+>>> outputs = model.predict(sentence, verbose=args.verbose)
+>>> mel_output = outputs["mel_output"]
+
+vocoder
+^^^^^^^^^^
+
+Like the example above, after loading the pretrained ConditionalWaveFlow model, call ``model.predict(mel)`` to synthesize waveflow (in numpy.ndarray format).
+
+>>> import soundfile as df
+>>> from parakeet.models import ConditionalWaveFlow
+
+>>> # load the pretrained model
+>>> checkpoint_dir = Path("waveflow_pretrained")
+>>> config = yacs.config.CfgNode.load_cfg(str(checkpoint_dir / "config.yaml"))
+>>> checkpoint_path = str(checkpoint_dir / "step-2000000")
+>>> vocoder = ConditionalWaveFlow.from_pretrained(config, checkpoint_path)
+>>> vocoder.eval()
+
+>>> # synthesize
+>>> audio = vocoder.predict(mel_output)
+>>> sf.write(audio_path, audio, config.data.sample_rate)
+
+For more details on how to use the model, please refer the documentation.
+
+
+

docs/install.rst

@@ -1,57 +1,63 @@
-# 安装
+=============
-
+安装
-[TOC]
+=============
 
 
-## 安装 PaddlePaddle
+安装 PaddlePaddle
-
+-------------------
-Parakeet 以 PaddlePaddle 作为其后端，因此依赖 PaddlePaddle，值得说明的是 Parakeet 要求 2.0 及以上版本的 PaddlePaddle。你可以通过 pip 安装。如果需要安装支持 gpu 版本的 PaddlePaddle，需要根据环境中的 cuda 和 cudnn 的版本来选择 wheel 包的版本。使用 conda 安装以及源码编译安装的方式请参考 [PaddlePaddle 快速安装](https://www.paddlepaddle.org.cn/install/quick/zh/2.0rc-linux-pip).
+Parakeet 以 PaddlePaddle 作为其后端，因此依赖 PaddlePaddle，值得说明的是 Parakeet 要求 2.0 及以上版本的 PaddlePaddle。你可以通过 pip 安装。如果需要安装支持 gpu 版本的 PaddlePaddle，需要根据环境中的 cuda 和 cudnn 的版本来选择 wheel 包的版本。使用 conda 安装以及源码编译安装的方式请参考 `PaddlePaddle 快速安装 <https://www.paddlepaddle.org.cn/install/quick/)>`_.
 
 **gpu 版 PaddlePaddle**
 
-```bash
+.. code-block:: bash
-python -m pip install paddlepaddle-gpu==2.0.0rc0.post101 -f https://paddlepaddle.org.cn/whl/stable.html
+
-python -m pip install paddlepaddle-gpu==2.0.0rc0.post100 -f https://paddlepaddle.org.cn/whl/stable.html
+    python -m pip install paddlepaddle-gpu==2.0.0rc1.post101 -f https://paddlepaddle.org.cn/whl/stable.html
-```
+    python -m pip install paddlepaddle-gpu==2.0.0rc1.post100 -f https://paddlepaddle.org.cn/whl/stable.html
+
 
 **cpu 版 PaddlePaddle**
 
-```bash
+.. code-block:: bash
-python -m pip install paddlepaddle==2.0.0rc0 -i https://mirror.baidu.com/pypi/simple
-```
 
-## 安装 libsndfile
+    python -m pip install paddlepaddle==2.0.0rc1 -i https://mirror.baidu.com/pypi/simple
 
-因为 Parakeet 的实验中常常会需要用到和音频处理，以及频谱处理相关的功能，所以我们依赖 librosa 和 soundfile 进行音频处理。而 librosa 和 soundfile  依赖一个 C 的库 libsndfile, 因为这不是 python 的包，对于 windows 用户和 mac 用户，使用 pip 安装 soundfile 的时候，libsndfile 也会被安装。如果遇到问题也可以参考 [SoundFile](https://pypi.org/project/SoundFile).
+
+安装 libsndfile
+-------------------
+
+因为 Parakeet 的实验中常常会需要用到和音频处理，以及频谱处理相关的功能，所以我们依赖 librosa 和 soundfile 进行音频处理。而 librosa 和 soundfile  依赖一个 C 的库 libsndfile, 因为这不是 python 的包，对于 windows 用户和 mac 用户，使用 pip 安装 soundfile 的时候，libsndfile 也会被安装。如果遇到问题也可以参考 `SoundFile <https://pypi.org/project/SoundFile>`_.
 
 对于 linux 用户，需要使用系统的包管理器安装这个包，常见发行版上的命令参考如下。
 
 
-```bash
+.. code-block:: 
-# ubuntu, debian
-sudo apt-get install libsndfile1
 
-# centos, fedora,
+    # ubuntu, debian
-sudo yum install libsndfile
+    sudo apt-get install libsndfile1
 
-# openSUSE
+    # centos, fedora,
-sudo zypper in libsndfile
+    sudo yum install libsndfile
-```
 
-## 安装 Parakeet
+    # openSUSE
+    sudo zypper in libsndfile
 
 
+安装 Parakeet
+------------------
+
 我们提供两种方式来使用 Parakeet.
 
-1. 需要运行 Parakeet 自带的实验代码，或者希望进行二次开发的用户，可以先从 github 克隆本工程，cd 仅工程目录，并进行可编辑式安装（不会被复制到 site-packages, 而且对工程的修改会立即生效，不需要重新安装），之后就可以使用了。
+#. 需要运行 Parakeet 自带的实验代码，或者希望进行二次开发的用户，可以先从 github 克隆本工程，cd 仅工程目录，并进行可编辑式安装（不会被复制到 site-packages, 而且对工程的修改会立即生效，不需要重新安装），之后就可以使用了。
 
-    ```bash
+   .. code-block:: bash
-    # -e 表示可编辑式安装
-    pip install -e .
-    ```
 
-2. 仅需要使用我们提供的训练好的模型进行预测，那么也可以直接安装 pypi 上的 wheel 包的版本。
+     # -e 表示可编辑式安装
+     pip install -e .
+
+
+#. 仅需要使用我们提供的训练好的模型进行预测，那么也可以直接安装 pypi 上的 wheel 包的版本。
+
+   .. code-block:: bash
+
+     pip install paddle-parakeet
 
-    ```bash
-    pip install paddle-parakeet
-    ```

parakeet/data/__init__.py

@@ -1,3 +1,5 @@
+"""Parakeet's infrastructure for data processing.
+"""
 # Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");