### Dependencies via Make or Setup

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/dependencies.md

List of dependencies that can be installed using make or a setup script.

```bash
kenlm
sox
mfa
openblas
kaldi
sctk
AutoLog
swig-decoder
python_kaldi_features
```

--------------------------------

### Setup Valgrind Tool

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/runtime/README.md

Installs the Valgrind tool by executing a setup script located in the tools directory. Ensure you are in the correct directory or provide the full path.

```bash
pushd tools
./setup_valgrind.sh
popd
```

--------------------------------

### Start MySQL and Milvus Services with Docker Compose

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/audio_searching/README.md

Navigate to the audio_searching directory and start the necessary services using Docker Compose. Ensure Docker Engine and Docker Compose are installed.

```bash
cd ~/PaddleSpeech/demos/audio_searching/
docker-compose -f docker-compose.yaml up -d
```

--------------------------------

### Navigate to Example Directory

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/asr/quick_start.md

Change the current directory to the 'examples/tiny' directory to access toy examples.

```bash
cd examples/tiny
```

--------------------------------

### PaddleSpeech Server Command Line Output Example

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/streaming_tts_server/README.md

This is an example of the log output when the PaddleSpeech server starts successfully via the command line.

```text
[2022-04-27 10:18:09,107] [    INFO] - The first response time of the 0 warm up: 1.1551103591918945 s
[2022-04-27 10:18:09,219] [    INFO] - The first response time of the 1 warm up: 0.11204338073730469 s
[2022-04-27 10:18:09,324] [    INFO] - The first response time of the 2 warm up: 0.1051797866821289 s
[2022-04-27 10:18:09,325] [    INFO] - **********************************************************************
INFO:     Started server process [17600]
[2022-04-27 10:18:09] [INFO] [server.py:75] Started server process [17600]
INFO:     Waiting for application startup.
[2022-04-27 10:18:09] [INFO] [on.py:45] Waiting for application startup.
INFO:     Application startup complete.
[2022-04-27 10:18:09] [INFO] [on.py:59] Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-27 10:18:09] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```

--------------------------------

### Streaming ASR Server Output Example

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/streaming_asr_server/README.md

Example output logs when starting the streaming ASR server, showing initialization steps and server status.

```text
[2022-05-14 04:56:13,086] [    INFO] - create the online asr engine instance
[2022-05-14 04:56:13,086] [    INFO] - paddlespeech_server set the device: cpu
[2022-05-14 04:56:13,087] [    INFO] - Load the pretrained model, tag = conformer_online_wenetspeech-zh-16k
[2022-05-14 04:56:13,087] [    INFO] - File /root/.paddlespeech/models/conformer_online_wenetspeech-zh-16k/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar.gz md5        checking...
[2022-05-14 04:56:17,542] [    INFO] - Use pretrained model stored in: /root/.paddlespeech/models/conformer_online_wenetspeech-zh-16k/asr1_chunk_conformer_wenetspeech_ckpt_1.  0.0a.model.tar
[2022-05-14 04:56:17,543] [    INFO] - /root/.paddlespeech/models/conformer_online_wenetspeech-zh-16k/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar
[2022-05-14 04:56:17,543] [    INFO] - /root/.paddlespeech/models/conformer_online_wenetspeech-zh-16k/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar/model.yaml
[2022-05-14 04:56:17,543] [    INFO] - /root/.paddlespeech/models/conformer_online_wenetspeech-zh-16k/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar/exp/               chunk_conformer/checkpoints/avg_10.pdparams
[2022-05-14 04:56:17,543] [    INFO] - /root/.paddlespeech/models/conformer_online_wenetspeech-zh-16k/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar/exp/               chunk_conformer/checkpoints/avg_10.pdparams
[2022-05-14 04:56:17,852] [    INFO] - start to create the stream conformer asr engine
[2022-05-14 04:56:17,863] [    INFO] - model name: conformer_online
[2022-05-14 04:56:22,756] [    INFO] - create the transformer like model success
[2022-05-14 04:56:22,758] [    INFO] - Initialize ASR server engine successfully.
INFO:     Started server process [4242]
[2022-05-14 04:56:22] [INFO] [server.py:75] Started server process [4242]
INFO:     Waiting for application startup.
[2022-05-14 04:56:22] [INFO] [on.py:45] Waiting for application startup.
INFO:     Application startup complete.
[2022-05-14 04:56:22] [INFO] [on.py:59] Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
[2022-05-14 04:56:22] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
```

--------------------------------

### Navigate to Example Directory

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/cls/quick_start.md

Change the current directory to the audio classification examples for ESC50.

```bash
cd examples/esc50/cls0
```

--------------------------------

### Install Miniconda and Initialize Conda

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/install.md

Downloads and installs Miniconda, then initializes the conda environment for shell usage.

```bash
# download the miniconda
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -P tools/
# install the miniconda
bash tools/Miniconda3-latest-Linux-x86_64.sh -b
# conda init
$HOME/miniconda3/bin/conda init
# use the "bash" command to make the conda environment works
bash
```

--------------------------------

### Install Sphinx and Theme

Source: https://github.com/paddlepaddle/paddlespeech/wiki/Build-Doc-for-PaddleSpeech-API

Installs Sphinx and the Read the Docs theme for documentation building.

```bash
pip install Sphinx sphinx_rtd_theme
```

--------------------------------

### Get Help for PaddleSpeech Server Command

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/streaming_tts_server/README.md

View available arguments and options for the paddlespeech_server start command.

```bash
paddlespeech_server start --help
```

--------------------------------

### Install Frontend Dependencies with Yarn

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/speech_web/README.md

Change to the web_client directory, install Yarn globally if not already present, and then use Yarn to install frontend dependencies. Node.js and npm are prerequisites.

```bash
cd web_client
# Install `yarn`, skip if already installed
npm install -g yarn
# Install frontend dependencies using yarn
yarn install
cd ../
```

--------------------------------

### Install PaddlePaddle and PaddleSpeech

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/install.md

Installs the PaddlePaddle deep learning framework and the PaddleSpeech library using specified PyPI mirrors. Ensure Python >= 3.7 is installed.

```bash
pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple
pip install paddlespeech -i https://pypi.tuna.tsinghua.edu.cn/simple
```

--------------------------------

### Download and Install Miniconda

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/install.md

Downloads the Miniconda installer, installs it silently, initializes conda for the current shell, and creates a Python 3.8 virtual environment.

```bash
# download the miniconda
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -P tools/
# install the miniconda
bash tools/Miniconda3-latest-Linux-x86_64.sh -b
# conda init
$HOME/miniconda3/bin/conda init
# use the "bash" command to make the conda environment works
bash
# create a conda virtual environment
conda create -y -p tools/venv python=3.8
# Activate the conda virtual environment:
conda activate tools/venv
# Install the conda packages
conda install -y -c conda-forge sox libsndfile swig bzip2 libflac bc
```

--------------------------------

### Install warpctc_pytorch

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/topic/ctc/ctc_loss_compare.ipynb

This snippet shows the output of installing the warpctc_pytorch library. It details the build process and final installation steps.

```shell
running install
running bdist_egg
running egg_info
writing warpctc_pytorch.egg-info/PKG-INFO
writing dependency_links to warpctc_pytorch.egg-info/dependency_links.txt
writing top-level names to warpctc_pytorch.egg-info/top_level.txt
writing manifest file 'warpctc_pytorch.egg-info/SOURCES.txt'
installing library code to build/bdist.linux-x86_64/egg
running install_lib
running build_py
running build_ext
building 'warpctc_pytorch._warp_ctc' extension
Emitting ninja build file /workspace/zhanghui/DeepSpeech-2.x/docs/topic/ctc/warp-ctc/pytorch_binding/build/temp.linux-x86_64-3.9/build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
ninja: no work to do.
g++ -pthread -B /workspace/zhanghui/DeepSpeech-2.x/tools/venv/compiler_compat -Wl,--sysroot=/ -shared -Wl,-rpath,/workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib -Wl,-rpath-link,/workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib -L/workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib -Wl,-rpath,/workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib -Wl,-rpath-link,/workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib -L/workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib /workspace/zhanghui/DeepSpeech-2.x/docs/topic/ctc/warp-ctc/pytorch_binding/build/temp.linux-x86_64-3.9/src/binding.o -L/workspace/zhanghui/DeepSpeech-2.x/docs/topic/ctc/warp-ctc/build -L/workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib/python3.9/site-packages/torch/lib -L/usr/local/cuda/lib64 -lwarpctc -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.9/warpctc_pytorch/_warp_ctc.cpython-39-x86_64-linux-gnu.so -Wl,-rpath,/workspace/zhanghui/DeepSpeech-2.x/docs/topic/ctc/warp-ctc/build
creating build/bdist.linux-x86_64/egg
creating build/bdist.linux-x86_64/egg/warpctc_pytorch
copying build/lib.linux-x86_64-3.9/warpctc_pytorch/__init__.py -> build/bdist.linux-x86_64/egg/warpctc_pytorch
copying build/lib.linux-x86_64-3.9/warpctc_pytorch/_warp_ctc.cpython-39-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg/warpctc_pytorch
byte-compiling build/bdist.linux-x86_64/egg/warpctc_pytorch/__init__.py to __init__.cpython-39.pyc
creating stub loader for warpctc_pytorch/_warp_ctc.cpython-39-x86_64-linux-gnu.so
byte-compiling build/bdist.linux-x86_64/egg/warpctc_pytorch/_warp_ctc.py to _warp_ctc.cpython-39.pyc
creating build/bdist.linux-x86_64/egg/EGG-INFO
copying warpctc_pytorch.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO
copying warpctc_pytorch.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying warpctc_pytorch.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying warpctc_pytorch.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt
zip_safe flag not set; analyzing archive contents...
warpctc_pytorch.__pycache__._warp_ctc.cpython-39: module references __file__
creating 'dist/warpctc_pytorch-0.1-py3.9-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it
removing 'build/bdist.linux-x86_64/egg' (and everything under it)
Processing warpctc_pytorch-0.1-py3.9-linux-x86_64.egg
removing '/workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib/python3.9/site-packages/warpctc_pytorch-0.1-py3.9-linux-x86_64.egg' (and everything under it)
creating /workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib/python3.9/site-packages/warpctc_pytorch-0.1-py3.9-linux-x86_64.egg
Extracting warpctc_pytorch-0.1-py3.9-linux-x86_64.egg to /workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib/python3.9/site-packages
warpctc-pytorch 0.1 is already the active version in easy-install.pth

Installed /workspace/zhanghui/DeepSpeech-2.x/tools/venv/lib/python3.9/site-packages/warpctc_pytorch-0.1-py3.9-linux-x86_64.egg
Processing dependencies for warpctc-pytorch==0.1
Finished processing dependencies for warpctc-pytorch==0.1
```

--------------------------------

### Start PaddleSpeech Server

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/README.md

Use this command to start the main PaddleSpeech server. Ensure you have a configuration file ready.

```shell
paddlespeech_server start --config_file ./demos/speech_server/conf/application.yaml
```

--------------------------------

### Install Triton Client

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/streaming_tts_serving_fastdeploy/README.md

Installs the Triton client library with all necessary dependencies for interacting with the serving endpoint.

```bash
pip3 install tritonclient[all]
```

--------------------------------

### Install Build Dependencies (Ubuntu)

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/TTSArmLinux/README.md

Installs essential build tools and utilities for compiling on Ubuntu systems.

```bash
# Ubuntu
sudo apt install build-essential cmake pkg-config wget tar unzip
```

--------------------------------

### PaddleSpeech Server Python API Output Example

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/streaming_tts_server/README.md

This is an example of the log output when the PaddleSpeech server starts successfully using the Python API.

```text
[2022-04-27 10:20:16,660] [    INFO] - The first response time of the 0 warm up: 1.0945196151733398 s
[2022-04-27 10:20:16,773] [    INFO] - The first response time of the 1 warm up: 0.11222052574157715 s
[2022-04-27 10:20:16,878] [    INFO] - The first response time of the 2 warm up: 0.10494542121887207 s
[2022-04-27 10:20:16,878] [    INFO] - **********************************************************************
INFO:     Started server process [23466]
[2022-04-27 10:20:16] [INFO] [server.py:75] Started server process [23466]
INFO:     Waiting for application startup.
[2022-04-27 10:20:16] [INFO] [on.py:45] Waiting for application startup.
INFO:     Application startup complete.
[2022-04-27 10:20:16] [INFO] [on.py:59] Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-27 10:20:16] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```

--------------------------------

### Run Main Demo Script

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/asr/quick_start.md

Execute the 'run.sh' script to start the main demonstration. Ensure each step works before proceeding to the next.

```bash
bash run.sh
```

--------------------------------

### Download and Setup MFA Tools

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/examples/other/tts_finetune/tts3/README.md

Download the Montreal Forced Aligner (MFA) tools and perform initial setup, including copying a shared library.

```bash
mkdir -p tools && cd tools
# mfa tool
wget https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner/releases/download/v1.0.1/montreal-forced-aligner_linux.tar.gz
tar xvf montreal-forced-aligner_linux.tar.gz
cp montreal-forced-aligner/lib/libpython3.6m.so.1.0 montreal-forced-aligner/lib/libpython3.6m.so
mkdir -p aligner && cd aligner
```

--------------------------------

### Prepare Data and Environment for Benchmark Training

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/tests/test_tipc/docs/benchmark_train.md

Run this script from the repository root to prepare training data and install necessary environments. It requires a configuration file and a mode argument.

```shell
bash test_tipc/prepare.sh test_tipc/configs/conformer/train_benchmark.txt benchmark_train
```

--------------------------------

### Run DeepSpeech2 Stages

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/examples/librispeech/asr0/README.md

Execute a range of stages in the DeepSpeech2 ASR example by specifying the start and stop stages.

```bash
bash run.sh --stage 2 --stop_stage 3
```

```bash
bash run.sh --stage 0 --stop_stage 0
```

--------------------------------

### Streaming TTS Client Output Example

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/streaming_tts_server/README.md

This is an example of the output logs produced by the streaming TTS client when run via the command line. It shows synthesis start, sentence processing, response times, audio duration, and save location.

```text
[2022-04-27 10:21:04,262] [    INFO] - tts websocket client start
[2022-04-27 10:21:04,496] [    INFO] - 句子：您好，欢迎使用百度飞桨语音合成服务。
[2022-04-27 10:21:04,496] [    INFO] - 首包响应：0.2124948501586914 s
[2022-04-27 10:21:07,483] [    INFO] - 尾包响应：3.199106454849243 s
[2022-04-27 10:21:07,484] [    INFO] - 音频时长：3.825 s
[2022-04-27 10:21:07,484] [    INFO] - RTF: 0.8363677006141812
[2022-04-27 10:21:07,516] [    INFO] - 音频保存至：output.wav
```

--------------------------------

### Install pytest-runner

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/install.md

Install 'pytest-runner' to potentially resolve issues with installing 'kaldiio' from its default download source. This is a prerequisite for installing PaddleSpeech.

```bash
# Some users may fail to install `kaldiio` due to the default download source, you can install `pytest-runner` at first；
pip install pytest-runner -i https://pypi.tuna.tsinghua.edu.cn/simple
```

--------------------------------

### Run TTS Frontend Demo with Help

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/TTSCppFrontend/README.md

Executes the TTS frontend demo and displays its command-line help information.

```bash
./run_front_demo.sh --help
```

--------------------------------

### Install PaddleSpeech

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/install.md

Install PaddleSpeech from the source code after cloning the repository. It's recommended to install `pytest-runner` first if `kaldiio` installation fails.

```bash
# Some users may fail to install `kaldiio` due to the default download source, you can install `pytest-runner` at first ;
pip install pytest-runner -i https://pypi.tuna.tsinghua.edu.cn/simple
# Make sure you are in the root directory of PaddleSpeech
pip install . -i https://pypi.tuna.tsinghua.edu.cn/simple
```

--------------------------------

### Download and Play Example Audio

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/tutorial/cls/cls_tutorial.ipynb

Downloads a sample audio file ('dog.wav') if it doesn't exist and then plays it using IPython.display.Audio.

```python
# 获取示例音频
!test -f ./dog.wav || wget https://paddlespeech.cdn.bcebos.com/PaddleAudio/dog.wav
IPython.display.Audio('./dog.wav')
```

--------------------------------

### Download and Install Miniconda

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/install.md

Download and install Miniconda for environment management on Linux/macOS. This script downloads the installer, installs it silently, initializes Conda, and activates the shell.

```bash
# download the miniconda
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -P tools/
# install the miniconda
bash tools/Miniconda3-latest-Linux-x86_64.sh -b
# conda init
$HOME/miniconda3/bin/conda init
# activate the conda
bash
```

--------------------------------

### Install PaddleSpeech

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/tutorial/cls/cls_tutorial.ipynb

Installs the necessary PaddleSpeech library and its dependencies. Ensure you have a compatible version of PaddlePaddle installed.

```python
# 环境准备：安装paddlespeech
!pip install -U pip paddlepaddle-gpu && pip install paddlespeech
```

--------------------------------

### Start PaddleSpeech Server via Command Line

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/streaming_tts_server/README.md

Use this command to start the PaddleSpeech server. Specify the configuration file for application settings. The default configuration uses HTTP.

```bash
paddlespeech_server start --config_file ./conf/tts_online_application.yaml
```

--------------------------------

### Prepare Benchmark Environment

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/tests/benchmark/conformer/README.md

Execute this script to set up the necessary environment for running the benchmark tests.

```bash
bash prepare.sh
```

--------------------------------

### Install PaddleAudio

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/audio/README.md

Use this command to install PaddleAudio via pip. Ensure you have Python and pip installed.

```bash
pip install paddleaudio
```

--------------------------------

### Set Installation Prefix

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/runtime/CMakeLists.txt

Specifies the installation directory for the project's artifacts to be within the build's 'install' subdirectory.

```cmake
set(CMAKE_INSTALL_PREFIX ${CMAKE_CURRENT_BINARY_DIR}/install)
```

--------------------------------

### Run Example with Custom Variables

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/examples/librispeech/asr2/README.md

Execute the run.sh script with custom values for --gpus and --avg_num to control GPU usage and model averaging.

```bash
bash run.sh --gpus 0,1 --avg_num 10
```

--------------------------------

### Install PaddleSpeech via Pip

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/README_cn.md

Installs PaddleSpeech and its necessary testing runner using pip. This is a quick installation method.

```shell
pip install pytest-runner
pip install paddlespeech
```

--------------------------------

### Start the API Server

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/audio_searching/README.md

Start the system server using FastAPI. Ensure the PYTHONPATH is set correctly to include the src directory.

```bash
export PYTHONPATH=$PYTHONPATH:./src
python src/audio_search.py
```

--------------------------------

### Install PaddlePaddle (CPU Version)

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/README_cn.md

Installs the CPU version of PaddlePaddle using pip. Ensure you have Python 3.8+ and GCC 4.8.5+ installed.

```shell
pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple
```

--------------------------------

### Generate API Docs (Example 2)

Source: https://github.com/paddlepaddle/paddlespeech/wiki/Build-Doc-for-PaddleSpeech-API

Generates API documentation for the paddlespeech package into the specified output directory.

```bash
sphinx-apidoc -o ./docs/source/api ./paddlespeech -f -e -M
```

--------------------------------

### Install SCLITE and Run G2P

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/examples/other/g2p/README.md

Installs the SCLITE tool for evaluation and then runs the G2P test. Ensure you have downloaded and extracted the BZNSYP dataset.

```bash
cd ../../../tools
bash extras/install_sclite.sh
cd -
./run.sh
```

--------------------------------

### Download Sample Audio Files

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/audio_tagging/README.md

Use wget to download sample WAV files for testing the audio tagging demo.

```bash
wget -c https://paddlespeech.cdn.bcebos.com/PaddleAudio/cat.wav https://paddlespeech.cdn.bcebos.com/PaddleAudio/dog.wav
```

--------------------------------

### Install Conda Dependencies for PaddleSpeech

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/install.md

Installs necessary dependencies like sox, libsndfile, and bzip2 using Conda. Ensure you have Conda installed and configured.

```bash
conda install -y -c conda-forge sox libsndfile bzip2
```

--------------------------------

### Install PaddleSpeech Backend Dependencies

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/speech_web/README.md

Navigate to the speech_server directory and install backend dependencies using pip. Ensure you have PaddleSpeech installed prior to this step.

```bash
cd speech_server
pip install -r requirements.txt -i https://mirror.baidu.com/pypi/simple
cd ../
```

--------------------------------

### Start Punctuation Service using Command Line

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/streaming_asr_server/README.md

Launches the punctuation service server from the command line. Ensure you are in the correct directory. The server defaults to CPU but can be configured for GPU.

```bash
In PaddleSpeech/demos/streaming_asr_server directory to launch punctuation service
paddlespeech_server start --config_file conf/punc_application.yaml
```

--------------------------------

### Install PaddleSpeech Package

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/install.md

Install the PaddleSpeech package from the root directory of the cloned repository. This command installs the library and makes its major functions available for use.

```bash
# Make sure you are in the root directory of PaddleSpeech
pip install . -i https://pypi.tuna.tsinghua.edu.cn/simple
```

--------------------------------

### Install GCC/G++ via Conda

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/install.md

Install specific versions of GCC and G++ using Conda. This is an alternative method for systems where direct installation might be complex or unavailable.

```bash
# Others
conda install -y -c gcc_linux-64=8.4.0 gxx_linux-64=8.4.0
```

--------------------------------

### Download Demo Sources

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/tutorial/tts/tts_tutorial.ipynb

Downloads necessary files for the TTS tutorial, including images, audio, and video.

```python
# download demo sources
!mkdir download
!wget -P download https://paddlespeech.cdn.bcebos.com/tutorial/tts/ocr_result.jpg
!wget -P download https://paddlespeech.cdn.bcebos.com/tutorial/tts/ocr.wav
!wget -P download https://paddlespeech.cdn.bcebos.com/tutorial/tts/tts_lips.mp4
```

--------------------------------

### Download and Prepare Pretrained Model

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/examples/librispeech/asr2/README.md

Download a pretrained ASR model, unpack it, and prepare data for testing. Assumes data processing might be skipped if manifests are already available.

```bash
wget https://paddlespeech.cdn.bcebos.com/s2t/librispeech/asr2/asr2_transformer_librispeech_ckpt_0.1.1.model.tar.gz
tar xzvf asr2_transformer_librispeech_ckpt_0.1.1.model.tar.gz
source path.sh
# If you have process the data and get the manifest file， you can skip the following 2 steps
bash local/data.sh --stage -1 --stop_stage -1
bash local/data.sh --stage 2 --stop_stage 2

CUDA_VISIBLE_DEVICES= ./local/test.sh conf/transformer.yaml exp/ctc/checkpoints/avg_10
```

--------------------------------

### Install PaddleSpeech Dependencies

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/audio_content_search/README.md

Install the necessary dependencies for PaddleSpeech by running this command.

```bash
pip install -r requirements.txt
```

--------------------------------

### Launch Speaker Verification Server

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/paddlespeech/server/README.md

Starts the speaker verification server using a specific configuration file.

```bash
paddlespeech_server start --config_file conf/vector_application.yaml
```

--------------------------------

### Install VAD Library and Dependencies

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/runtime/engine/vad/nnet/CMakeLists.txt

Installs the VAD library and platform-specific glog library.

```cmake
file(RELATIVE_PATH DEST_DIR ${ENGINE_ROOT} ${CMAKE_CURRENT_SOURCE_DIR})
install(TARGETS pps_vad DESTINATION lib)
if(ANDROID)
    install(TARGETS extern_glog DESTINATION lib)
else() # UNIX
    install(TARGETS glog DESTINATION lib)
endif()
```

--------------------------------

### Install PaddleSpeech and PaddlePaddle

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/tutorial/st/st_tutorial.ipynb

Installs the latest versions of PaddleSpeech and PaddlePaddle (GPU version).

```python
!pip install -U pip paddlepaddle-gpu && pip install paddlespeech
```

--------------------------------

### Download Sample Audio File

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/speech_ssl/README.md

Use wget to download a sample English audio file for testing the Speech SSL demo.

```bash
wget -c https://paddlespeech.cdn.bcebos.com/PaddleAudio/en.wav
```

--------------------------------

### Install Conda Packages

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/install.md

Installs necessary audio and development packages using conda.

```bash
# Install the conda packages
conda install -y -c conda-forge sox libsndfile swig bzip2 libflac bc
```

--------------------------------

### Install pytest-benchmark

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/audio/tests/benchmark/README.md

Install the pytest-benchmark package using pip. This is a prerequisite for running the benchmarks.

```sh
pip install pytest-benchmark
```

--------------------------------

### Run Main Entry Point for Audio Classification

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/docs/source/audio/cls/quick_start.md

Execute the main script to start the audio classification process. Adjust CUDA_VISIBLE_DEVICES for GPU or CPU usage.

```bash
CUDA_VISIBLE_DEVICES=0 ./run.sh 1
```

--------------------------------

### Start Streaming ASR Server

Source: https://github.com/paddlepaddle/paddlespeech/blob/develop/demos/streaming_asr_server/web/readme.md

Starts the streaming ASR server using a specified configuration file. Navigate to the demo directory and execute this command.

```bash
cd PaddleSpeech/demos/streaming_asr_server
paddlespeech_server start --config_file conf/ws_conformer_wenetspeech_application_faster.yaml
```