Python script for extracting audio from video files and creating Mel spectrograms

Overview

video2spectrogram

supported versions Tweet

About

This package is meant to automate the process of extracting audio files from videos and saving the plots computed from these audio frequencies in the Mel scale (Sectrogram). Videos are processed in parallel with the audio extracted by ffmpeg stored in .wav files which are then used to create spectrograms stored as .JPEG and can be used by any audio-based method.

Currently supported video formats include .mp4,mpeg-4,.avi,.wmv. If you have a different extension, you can simply change the script to include them (in the video2spectrogram/get_spectrogram.py)


Package requirements

  • librosa
  • numpy
  • matplotlib

Make sure that the above packages are installed before running any functions.

ffmpeg: You will need to have installed ffmpeg in order to perform the audio extraction from the video files.

Multiprocessing: The code uses multiprocessing for improving speeds, thus the total time required for the conversion varies across different processors. The code has been tested on an AMD Ryzen 3950X with an average conversion time of 4 minutes for ~1K videos (with an average resolution of 480p and length of 5s.)


Dataset structure

The package assumes a fixed video dataset structure:


   
        
  │
  └──
    
     
  │     │
  │     │─── 
     
      
  │     │─── 
      
       
  │     │─── ...
  │    ...      
  │
  └───
       
         │ │ │ │─── 
        
          │ │─── 
         
           │ │─── ... ... ... 
         
        
       
      
     
    
   

Usage

The main code is at the get_spectrograme.py file. To run the convertor simply call the convert function with the base directory of the dataset and the destination directory for where to save the audio. Additional arguments that can be used:

  • verbose_lvl: Integer for verbosity.
  • save_wav: Boolean to determine if the created wav files are to be stored and not deleted.
  • ar: Integer for the ffmpeg option for specifying the audio sampling frequency.
  • res_h: Integer for the height of the spectrogram image to be saved.
  • res_w: Integer for the width of the spectrogram image to be saved.
  • dpi: Integer for the display's dot's per inch. Needs to be set to avoid inconsistencies to the res argument.
from video2spectrogram import convert
#or
from get_spectrogram import convert

convert(my_dataset_dir, my_target_dir)

Installation through git

Please make sure, Git is installed in your machine:

$ sudo apt-get update
$ sudo apt-get install git
$ git clone https://github.com/alexandrosstergiou/video2spectrogram.git
$ cd dataset2database
$ pip install .

You can then use it as any other package installed through pip.


Installation through pip

The latest stable release is also available for download through pip

$ pip install video2spectrogram
You might also like...
Streamlink is a CLI utility which pipes video streams from various services into a video player

Streamlink is a CLI utility which pipes video streams from various services into a video player

Filtering user-generated video content(SberZvukTechDays)Filtering user-generated video content(SberZvukTechDays)
Filtering user-generated video content(SberZvukTechDays)Filtering user-generated video content(SberZvukTechDays)

Filtering user-generated video content(SberZvukTechDays) Table of contents General info Team members Technologies Setup Result General info This is a

Telegram Video Chat Video Streaming bot 🇱🇰
Telegram Video Chat Video Streaming bot 🇱🇰

🧪 Get SESSION_NAME from below: Pyrogram 🎭 Preview ✨ Features Music & Video stream support MultiChat support Playlist & Queue support Skip, Pause, Re

Play Video & Music on Telegram Group Video Chat
Play Video & Music on Telegram Group Video Chat

🖤 DEMONGIRL 🖤 ʜᴇʟʟᴏ ❤️ 🇱🇰 Join us ᴠɪᴅᴇᴏ sᴛʀᴇᴀᴍ ɪs ᴀɴ ᴀᴅᴠᴀɴᴄᴇᴅ ᴛᴇʟᴇʀᴀᴍ ʙᴏᴛ ᴛʜᴀᴛ's ᴀʟʟᴏᴡ ʏᴏᴜ ᴛᴏ ᴘʟᴀʏ ᴠɪᴅᴇᴏ & ᴍᴜsɪᴄ ᴏɴ ᴛᴇʟᴇɢʀᴀᴍ ɢʀᴏᴜᴘ ᴠɪᴅᴇᴏ ᴄʜᴀᴛ 🧪 ɢ

Turn any live video stream or locally stored video into a dataset of interesting samples for ML training, or any other type of analysis.
Turn any live video stream or locally stored video into a dataset of interesting samples for ML training, or any other type of analysis.

Sieve Video Data Collection Example Find samples that are interesting within hours of raw video, for free and completely automatically using Sieve API

Video-to-GIF-Converter - A small code snippet that can be used to convert any video to a gif

Video to GIF Converter Project Description: This is a small code snippet that ca

Video-stream - A telegram video stream bot repo
Video-stream - A telegram video stream bot repo

This is a Telegram Video stream Bot. Binary Tech 💫 Features stream videos downl

Terminal-Video-Player - A program that can display video in the terminal using ascii characters

Terminal-Video-Player - A program that can display video in the terminal using ascii characters

TkVideoplayer - This is a simple library to play video files in tkinter.
TkVideoplayer - This is a simple library to play video files in tkinter.

TkVideoplayer - This is a simple library to play video files in tkinter.

Releases(v0.1)
Owner
Alexandros Stergiou
Computer Vision and Machine Learning Researcher
Alexandros Stergiou
PyAV is a Pythonic binding for the FFmpeg libraries.

PyAV is a Pythonic binding for the FFmpeg libraries. We aim to provide all of the power and control of the underlying library, but manage the gritty details as much as possible.

PyAV 1.8k Jan 01, 2023
All the code in these repos was created and explained by HashLips on the main YouTube channel.

Welcome to HashLips 👄 All the code in these repos was created and explained by HashLips on the main YouTube channel. To find out more please visit: ?

HashLips 6.7k Jan 06, 2023
A way to run youtube videos in TTY

TTY youtube client its finally here, the one thing literally NO ONE ASKED FOR!! A way to run youtube videos in TTY Dependencies: (pip) yt-search (syst

1 Nov 28, 2021
A telegram bot for compressing/encoding videos in h264 format.

Video-Encoder-Bot a telegram bot for compressing/encoding videos in h264 format. Configuration Add values in environment variables or add them in conf

Weeb >.< 61 Dec 29, 2022
Adblocker for movie subtitles.

SubAdBlock Adblocker for movie subtitles. Usage Place "main.py" and "config.conf" in directory with subtitles and run "main.py". It will automatically

Marko Živić 1 Jan 09, 2022
LL-HLS implementation written in Python3

biim mpegts stream to Apple Low Latency HLS Feature mpegts demuxing in pure python3 (using asyncio) mpegts stream to fragmented ts use piping from ffm

もにょ~ん 15 Jan 03, 2023
Stream deck using Arduino and Python

Stream deck using Arduino and Python This is a little project I started due to the fact that I wanted to stream and didn't want to spend lots on a sim

Tal Cherniavsky 2 Feb 11, 2022
Python program - to extract slides from videos

Programa em Python - que fiz em algumas horas e que provavelmente tem bugs - para extrair slides de vídeos.

Natanael Antonioli 45 Nov 12, 2022
Code for the manim-generated scenes used in 3blue1brown videos

Code for the manim-generated scenes used in 3blue1brown videos

Grant Sanderson 4.1k Jan 09, 2023
Cvplayer - A simple video player written in python using ffpyplayer and OpenCV

Video Player cvplayer is a minimal wrapper around the ffpyplayer.MediaPlayer cla

ADI 7 Dec 19, 2022
This is an example of building a video Question-Answer system using Jina.

example-video-search This is an example of building a video Question-Answer system using Jina. The index data is subtitle files of YouTube videos. Aft

Jina AI 9 Oct 18, 2022
Stream music with ffmpeg and python

youtube-stream Stream music with ffmpeg and python original Usage set the KEY in stream.sh run server.py run stream.sh (You can use Git bash or WSL in

Giyoung Ryu 14 Nov 17, 2021
A free project by a normal kamenrider fan

DEMONS DRIVER Python + OpenCV demons.py采集原视频中led灯珠颜色,并将结果输出到output文件夹 Arduino + WS2812B 基于FastLED 实现DEMONS驱动器的led面板效果 项目未完成,持续更新中 --------------------

2 Nov 14, 2022
Streams video from raspberry pi to desktop T1 - Recognizes Faces on client T2

VideoStreamingServer Completed: Streams video from raspberry pi to desktop T1 - Recognizes Faces on client T2 In progress: Change the transmission Pro

1 Dec 06, 2021
A Python extension that provides bindings to WebRTC M92

This project follows the W3C specification with some modifications and additions to make it work better with Python applications, with useful APIs like programmatic audio and video.

Il'ya 104 Dec 26, 2022
Filtering user-generated video content(SberZvukTechDays)Filtering user-generated video content(SberZvukTechDays)

Filtering user-generated video content(SberZvukTechDays) Table of contents General info Team members Technologies Setup Result General info This is a

Roman 6 Apr 06, 2022
Python package for Near Duplicate Video Detection (Perceptual Video Hashing) - Get a 64-bit comparable hash-value for any video.

The Python package for near duplicate video detection ⭐️ Introduction Videohash is a Python package for detecting near-duplicate videos (Perceptual Vi

Akash Mahanty 144 Dec 19, 2022
Repository to create Ascii art in CMD based on video file.

Made to take any file format, and transform it into ascii art, displayed as a video in the cmd. If the cmd formatting is wrong, try zooming a little and remember to make cmd fullscreen. I made my cmd

60 Dec 17, 2022
Automatic video generator for local news

Automatic video generator for local news

Gabriel Monteiro 2 Jan 11, 2022
This application makes a webrtc video call with jitsi meet signaling

gstreamer-jitsi-meet This application makes a webrtc video call with jitsi meet signaling. Other end can be any jitsi meet app or web app. It doesn't

Linh 7 Apr 26, 2022