# SongRecogn

**Repository Path**: keyestore/SongRecogn

## Basic Information

- **Project Name**: SongRecogn
- **Description**: 一个使用 Shazam 算法的歌曲识别程序
- **Primary Language**: Python
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-04-24
- **Last Updated**: 2026-04-24

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

SongRecogn
==========

This is a song recognition program using shazam's algorithm.

[Paper](http://www.ee.columbia.edu/~dpwe/papers/Wang03-shazam.pdf)

If you want to see a explaination of how it works, check this out(chinese ver. only):[
Here](https://www.bilibili.com/read/readlist/rl54978)


## Setup
Make sure you install all dependency in the requirements.txt

**Change Config: Change the sqlalchemy url in srModule/Config to your own database.**

Create tables by using createDatabase.py

`python createDatabase.py`

*Change the config of mysql to reach a higher performance*

## Quickstart
```
cd SongRecogn
python SongRecogn.py
```

waiting for program connect to the data base.

then you will see a console.

```
add-audio : add a audio to the database
           usage :add-audio song/lingyu.mp3
add-dir : add audio from a directory
         usage :add-audio song
recognize : recognzie a audio sample from file
           usage :recognzie sample/lingyu_01.mp3
help : show help
quit : Quit
```

type the command to use the console.

![open console](plot/c2.JPG)
![add song](plot/c6.JPG)
![recognzie](plot/c9.JPG)

If you want to use it directly in script.

```
from srModule import Console
Console.addAudio("song/linagyu.mp3")
Console.recognizeAudio("songp/liangyu_06.mp3")
Console.addAudioFromDir("song")
```

## ABC
3 sec of sample audio already have a very higher accuracy.

The longersample audio are, the longer time it costs for recognizing.



## Thanks

Thanks:

[dejavu](https://github.com/worldveil/dejavu)


## Change Log

2019/4/4: Increase inserting speed 

2019/4/6: Fix potential memory issue + add mutliprocessing support in recognizing.