How to use #Vosk -- the Offline Speech Recognition Library for Python

I've used the #SpeechRecognition Python Library extensively in many of projects on my channel, but I will need an offline speech recognition library for future projects. So in this video, I'll be showing you how to install #vosk the offline speech recognition library for Python.

Tip Jar:
Bitcoin: 1AkfvhGPvTXMnun4mx9D6afBXw5237jF9W

[edsonservi]

Muito legal irmão!!! Sei que fala inglês, mas traduzir é fácil. Adorei o vídeo. Estou iniciando em python e estava com dificuldades de converter fala em texto, principalmente pela questão de ser "off-line" o que eu preciso! Muito obrigado!!!

[aaronstarkweather]

Didn't realize that this would solve my biggest nemesis which has been installing PyAudio. Omg thank you!

[ardavanorakzade]

It was an awesome tutorial and exactly what I was looking for, thanks very much.

[daramolaoluwafemimichael]

This is just what I've been looking for. Thanks brandon🖒

[sixfree]

I've wanted to do this project ever since the IBM activa commercial way back in like 1990 :D looks like the tech is finally getting close!

[raymorganti]

Awesome tutorial! Exactly what I needed.

[S-Technology]

Great Tutorial! I used it to add vosk to my own JARVIS system.
I don't know if others mentioned it, but to fix the problem with the mic not being able to be shared you can change 1 line of code in your example.
change:
data = stream.read(4096)
to
data = stream.read(4096, exception_on_overflow = False)

I can talk to my assistant and have OBS recording from the same microphone at the same time.

[professeurredstone]

It works very well for French model thank you !

[jc.daguila]

Excellent tutorial, Thank You so much!

[code-grammardude]

very glad vosk some more attention. I think it's very underrated

[CountryHouseIncubators]

Is there a way to take the vosk model and add words that it can recognize?

[MicrobeHg]

Thanks for the tutorial, it's really helpful XD

[hartoflearning]

Can I save the model on my D drive and run it from there with the absolute path?

[seraph]

also pyaudio is now installable on python 3.10 on windows with pip I just tried it for giggles, , and it worked :D

[amoawesomeart]

File "C:\Python\Python37\lib\site-packages\vosk\__init__.py", line 138, in __init__
self._handle = _c.vosk_recognizer_new(args[0]._handle, args[1])
AttributeError: 'str' object has no attribute '_handle'

Got the vosk and pyaudio installed without any problems, however when I try to run the script as written in the video it's unable to locate the model location as it tosses the above error at me.

[crunckNATIon]

awesome was looking for documentation for vosk online and it wasnt much...and they few others were either medium articles or stack overflow...but most solid source ive seen is this video...i just which it show how write it to a file, and the key interrupt that you were talking about. sorry for the rant but awesome video

[-RobGPT-]

focken hell, this video was buffering in the background and suddenly started playing while i was coding, thought my language model had come alive for a few seconds there lmao

[judelfenix]

thank you bro, i can now start my project

[jloibman]

I'm getting an error when trying to create a Model: "Exception: Failed to create a model"... Do you know how to fix? Thanks.

[egrammar]

Thanks for the details, Could you please help us understand how "elsa speaking app" pronunciation error identification works. What is the logic and code behind it.