jim-schwoebel / voicebook Goto Github PK

🗣️ A book and repo to get you started programming voice computing applications in Python (10 chapters and 200+ scripts).

Home Page: https://neurolex.ai/voicebook

License: Apache License 2.0

Python 83.34% HTML 1.97% MATLAB 0.04% Makefile 0.22% C++ 14.38% Dockerfile 0.01% SWIG 0.04%

voice voice-assistant voice-recognition voice-recording transcription featurization data data-cleaning visualization generation voice-activity-detection voice-control server security encryption-decryption python3 machine-learning wake-word-detection voice-computing

voicebook's Introduction

Voicebook

This is an assortment of all the scripts associated with the Intro to Voice Computing Book. These scripts should give you a jumpstart in learning how to write Python code for voice-related applications.

^^ Note: If you find this code useful, please leave a star :) ^^

Getting started: setting up environment (mac)

Watch the overview video for this book here.

Note that these are the instructions for Mac computers; you may need some custom setup for FFmpeg and/or SoX if you're using a Windows and/or Linux computer.

First, clone the repository and submodules:

git clone --recurse-submodules -j8 https://github.com/jim-schwoebel/voicebook

Now you need to run the setup.py script in a virtual environment to make sure you have all the required dependencies for all the chapters of the book. To do this, run:

cd voicebook
pip3 install virtualenv
virtualenv env 
source env/bin/activate
python3 setup.py

Now you have all the dependencies necessary to follow along with the chapters in the book. You don’t need to worry about any other installations.

License

This repository is licensed under the Apache 2.0 License.

Feedback

Any feedback on the book or this repository is greatly appreciated.

If you find something that is missing or doesn't work, please consider opening a GitHub issue.
If you'd like to be mentored by someone on our team, check out the Innovation Fellows Program.
If you are looking for a framework to start building machine learning models in voice computing, check out Allie.
If you want to talk to me directly, please send me an email @ [email protected].

Citation

Please use the following citation when citing this book in your research work:

Schwoebel, J. (2018). An Introduction to Voice Computing in Python. Boston; Seattle; Atlanta: NeuroLex Laboratories. https://github.com/jim-schwoebel/voicebook

References

Check out the wiki or documentation below to follow along with each chapter in the book. In this way, you can get quickly up to speed with the 200+ scripts included in this repository.

voicebook's People

Stargazers

Watchers

Forkers

gridl ilyaselitser wxb506 bbruhh sherryxtchen fancyerii sovsem1234 kopankom airob ncouturier hadryan qo6xup6 srinivasgutta7 mukul96 corelon xrick krokodilj dwtcourses ittech25 neurolexdiagnostics surveylex luquesky guomin ttslr isehd lwarrenburg smallflyingpig qgzang boukos ajayarunachalam mirzaabazovic shrutikshirsagar ghhabib2 slbinilkumar chichimi7 pu55yf3r neurolexco neurolex-diagnostics wahidmounir protea-earth saadmann18 co18325 louismoura madkote songys garrywrj ajinkyakulkarni14 dareenharthi sanyaade-machine-learning riskysignal cspsolutions-dev ankitshah009 bobthehands windowxiaoming achyun mariumaz zlszhonglongshen lexi5577 muflhi01 athenasaurav rkijak reptilefury seanahmad zhazhafon bryx rushikhetani mehmet-zahid coreymakes mgm79 audiowiz sanyaade-teachings thefenrislycaon kalideir mike100101100011 knpubscripts harel-coffee technophobe01 nasim-alamdari kelseyicotton althetinkerer ddeveloperr

voicebook's Issues

Chapter 7 - Page 269 - grammar error

Top of page --> however, if you __this code __ has a few issues.

Need to change to --> However, if you look at this code you'll notice a few issues:

Introduction timeline suggestion

Add Radio Rex to timeline (1912).

https://ileriseviye.wordpress.com/2011/02/17/speech-recognition-in-1920s-radio-rex-the-first-speech-recognition-machine/

Chapter 9 - page 370 - "they have recently have..."

Last paragraph - "I doubt Google is doing this as they have recently HAVE stepped away..."

Get rid of the second have.

Acknowledgements, Page 7 - Innovation Fellows

The Innovation Fellows sections has a period after Timothy Wroge and Allison Pei. These periods should be removed and replaced with commas.

Chapter 6 - Add Kibana / Elasticsearch part of the book (2nd edition)

Chapter 6 - visualization. Add an elastic search / kibana section.

Chapter 4 - Deep learning optimization

Introduce AutoML techniques just like in classification.

I am having trouble installing the Voicebook on Linux

The book was intended mostly for Mac OSs here, but you can definitely run this on Linux. You just need to custom setup FFmpeg and Sox using:

sudo apt-get install sox
sudo apt-get install ffmpeg

You also need to modify the requirements.txt here to work on linux. I have attached a different requirements.txt here and you can run this command:

pip3 install -r requirements.txt

And the rest of the modules should install. I believe the only modules that cannot be installed on linux are:

pyobjc-framework-Accounts==6.2
pyobjc-framework-AddressBook==6.2
pyobjc-framework-AdSupport==6.2
pyobjc-framework-AppleScriptKit==6.2
pyobjc-framework-AppleScriptObjC==6.2
pyobjc-framework-ApplicationServices==6.2
pyobjc-framework-AuthenticationServices==6.2
pyobjc-framework-AutomaticAssessmentConfiguration==6.2
pyobjc-framework-Automator==6.2
pyobjc-framework-AVFoundation==6.2
pyobjc-framework-AVKit==6.2
pyobjc-framework-BusinessChat==6.2
pyobjc-framework-CalendarStore==6.2
pyobjc-framework-CFNetwork==6.2
pyobjc-framework-CloudKit==6.2
pyobjc-framework-Cocoa==6.2
pyobjc-framework-Collaboration==6.2
pyobjc-framework-ColorSync==6.2
pyobjc-framework-Contacts==6.2
pyobjc-framework-ContactsUI==6.2
pyobjc-framework-CoreAudio==6.2
pyobjc-framework-CoreAudioKit==6.2
pyobjc-framework-CoreBluetooth==6.2
pyobjc-framework-CoreData==6.2
pyobjc-framework-CoreHaptics==6.2
pyobjc-framework-CoreLocation==6.2
pyobjc-framework-CoreMedia==6.2
pyobjc-framework-CoreMediaIO==6.2
pyobjc-framework-CoreML==6.2
pyobjc-framework-CoreMotion==6.2
pyobjc-framework-CoreServices==6.2
pyobjc-framework-CoreSpotlight==6.2
pyobjc-framework-CoreText==6.2
pyobjc-framework-CoreWLAN==6.2
pyobjc-framework-CryptoTokenKit==6.2
pyobjc-framework-DeviceCheck==6.2
pyobjc-framework-DictionaryServices==6.2
pyobjc-framework-DiscRecording==6.2
pyobjc-framework-DiscRecordingUI==6.2
pyobjc-framework-DiskArbitration==6.2
pyobjc-framework-DVDPlayback==6.2
pyobjc-framework-EventKit==6.2
pyobjc-framework-ExceptionHandling==6.2
pyobjc-framework-ExecutionPolicy==6.2
pyobjc-framework-ExternalAccessory==6.2
pyobjc-framework-FileProvider==6.2
pyobjc-framework-FileProviderUI==6.2
pyobjc-framework-FinderSync==6.2
pyobjc-framework-FSEvents==6.2
pyobjc-framework-GameCenter==6.2
pyobjc-framework-GameController==6.2
pyobjc-framework-GameKit==6.2
pyobjc-framework-GameplayKit==6.2
pyobjc-framework-ImageCaptureCore==6.2
pyobjc-framework-IMServicePlugIn==6.2
pyobjc-framework-InputMethodKit==6.2
pyobjc-framework-InstallerPlugins==6.2
pyobjc-framework-InstantMessage==6.2
pyobjc-framework-Intents==6.2
pyobjc-framework-IOSurface==6.2
pyobjc-framework-iTunesLibrary==6.2
pyobjc-framework-LatentSemanticMapping==6.2
pyobjc-framework-LaunchServices==6.2
pyobjc-framework-libdispatch==6.2
pyobjc-framework-LinkPresentation==6.2
pyobjc-framework-LocalAuthentication==6.2
pyobjc-framework-MapKit==6.2
pyobjc-framework-MediaAccessibility==6.2
pyobjc-framework-MediaLibrary==6.2
pyobjc-framework-MediaPlayer==6.2
pyobjc-framework-MediaToolbox==6.2
pyobjc-framework-Metal==6.2
pyobjc-framework-MetalKit==6.2
pyobjc-framework-ModelIO==6.2
pyobjc-framework-MultipeerConnectivity==6.2
pyobjc-framework-NaturalLanguage==6.2
pyobjc-framework-NetFS==6.2
pyobjc-framework-Network==6.2
pyobjc-framework-NetworkExtension==6.2
pyobjc-framework-NotificationCenter==6.2
pyobjc-framework-OpenDirectory==6.2
pyobjc-framework-OSAKit==6.2
pyobjc-framework-OSLog==6.2
pyobjc-framework-PencilKit==6.2
pyobjc-framework-Photos==6.2
pyobjc-framework-PhotosUI==6.2
pyobjc-framework-PreferencePanes==6.2
pyobjc-framework-PubSub==6.2
pyobjc-framework-PushKit==6.2
pyobjc-framework-Quartz==6.2
pyobjc-framework-QuickLookThumbnailing==6.2
pyobjc-framework-SafariServices==6.2
pyobjc-framework-SceneKit==6.2
pyobjc-framework-ScreenSaver==6.2
pyobjc-framework-ScriptingBridge==6.2
pyobjc-framework-SearchKit==6.2
pyobjc-framework-Security==6.2
pyobjc-framework-SecurityFoundation==6.2
pyobjc-framework-SecurityInterface==6.2
pyobjc-framework-ServiceManagement==6.2
pyobjc-framework-Social==6.2
pyobjc-framework-SoundAnalysis==6.2
pyobjc-framework-Speech==6.2
pyobjc-framework-SpriteKit==6.2
pyobjc-framework-StoreKit==6.2
pyobjc-framework-SyncServices==6.2
pyobjc-framework-SystemConfiguration==6.2
pyobjc-framework-SystemExtensions==6.2
pyobjc-framework-UserNotifications==6.2
pyobjc-framework-VideoSubscriberAccount==6.2
pyobjc-framework-VideoToolbox==6.2
pyobjc-framework-Vision==6.2
pyobjc-framework-WebKit==6.2

Intro - publishing mediums into intro

Put all the modern places to publish voice media in the introductory chapter.

This is currently in building voice computer chapter.

Thanks! LSTM wanted...

Hi, many Thanks for great overview and samples - I defently will recommend this information as "start with".

Would be nice also to add CNN and RNN for audio classification.

Chapter 6, Visualization. Page 214 - Resize footnote #247.

Vector quantization, footnote #247 is a different size than all other footnoes.

Ongoing list of suggestions (book 2)

Introduction

Add Radio Rex to timeline (1912). https://ileriseviye.wordpress.com/2011/02/17/speech-recognition-in-1920s-radio-rex-the-first-speech-recognition-machine/

Chapter 1 - Collection
-Add in James comments about a short demo to collect audio away and close to microphone to make the lesson more intuitive. In feedback folder on google drive.

Chapter 3 - Featurization

Cosine similarity - add this to chapter http://blog.christianperone.com/2013/09/machine-learning-cosine-similarity-for-vector-space-models-part-iii/

Chapter 4 - Modeling

Introduce AutoML techniques just like in classification.

Chapter 6 - Visualization

Add an elastic search / kibana section.

Chapter 3 - Featurization

homebrew install

homebrew install not mentioned in voicebook prior to python3 setup ('install' missing)?).

Chapter 1 - Youtube collection tools

Add youtube collection tools to CHAPTER 1 - collection chapter

Move from modeling chapter to this chapter.

Help with labeling data, etc.

Chapter 7 - Page 262 - Resize footnote #280.

Footnote 280 is a larger size than all other footnotes. Resize it so it is the proper size.

Book - typo - page 103 - MEMUPPS voice controls

User control - assume distance of 3 meters away from microphone.

Did you mean 3 feet??

typo - page 150

lightening --> lightning (first sentence)

Acknowledgements

Fix some grammar mistakes / typos

Mis-spelling .- generaiting audio data (Page 190)

Fix mispelling in next edition of book.

Chapter 1 - collection

Add in James comments about a short demo to collect audio away and close to microphone to make the lesson more intuitive.

In feedback folder on google drive.

fatal: The remote end hung up unexpectedly fatal: early EOF fatal: index-pack failed

This is often due to a slow internet connection.

For a resolution, see https://stackoverflow.com/questions/38618885/error-rpc-failed-curl-transfer-closed-with-outstanding-read-data-remaining

====

It happens more often than not, I am on a slow internet connection and I have to clone a decently-huge git repository. The most common issue is that the connection closes and the whole clone is cancelled.

Cloning into 'large-repository'...
remote: Counting objects: 20248, done.
remote: Compressing objects: 100% (10204/10204), done.
error: RPC failed; curl 18 transfer closed with outstanding read data remaining 
fatal: The remote end hung up unexpectedly
fatal: early EOF
fatal: index-pack failed

After a lot of trial and errors and a lot of “remote end hung up unexpectedly” I have a way that works for me. The idea is to do a shallow clone first and then update the repository with its history.

$ git clone http://github.com/large-repository --depth 1
$ cd large-repository
$ git fetch --unshallow