I am 78 years old and sadly experiencing the ravages of time such that my comprehension and memory are not what they once were, added to that I have only one hand for typing and my control of that is much reduced due to a stroke.
I am looking for speech recognition software that would integrate with Libre Office and allow me to write documents without having to actually type.
Can any one tell me if any easily installed and used software exists that would meet my requirements.
You can also Google for more FOSS voice recognition engines,
But don’t know how you’d do…
Ordinarily I look at a FOSS project’s history, recommendations and uses before deciding on something that appears to be well maintained and reputable.
But, I wouldn’t be able to apply same criteria to a voice recognition engine,
The problem is that the advances in GPU hardware since 2014 and related machine learning AI has been a generational revolution for technologies like voice recognition so older engines might not be able to utilize the new features developed only within the past 2-3 years.
Ever notice how a phone manufactured recently is sooooo much better at voice recognition than older phones? You don’t need to train your voice software? It’ll understand what is being said no matter your dialect? And, it’s fast?
That’s largely the benefits of AI based voice recognition where typically enormous amounts of spoken text has been fed into a program long ago, analyzed for accurate recognition and then the algorithms stored on your device,ready to match your real time voice input.
That’s a lot different than how previous engines worked which often stored actual words spoken different ways.
If you can actually find a very recent voice recognition engine with hardly any history…
It might be a better choice than anything with a reputation.
I too, am looking for a SPEECH-TO-TEXT feature / software, that I can speak my words into things like LibreOffice, gNote, Kate, Kwrite, and Web Browser places (like this one), because my typing is bad. Currently, I CAN use the Google DOCs one, and MS Word 365, FWIW.
I have tried to help out a neighbour with speech to text and text to speech software. Husband uses Linux systems.
I came across big problems, as there appears to be no solutions within the openSUSE repros.
However moving To Windows 10 gave access to a number of solution including “Narrator” within Windows 10 and when using Google Chrome to their docs and Voice Typing.
When trying Google Voice Typing in “Chromium”, the results were not as good.
This accessibility lack inside openSUSE of a free and in repositories access to both speech reading and voice to text seems a major lack.
while Orca was referenced it needed Gnome rather than the base KDE systems of openSUSE
Has anyone used Orca and what kind of results does it give?
If they used other speech recognition software or voice to text software acn theyadvise what works and how to put it inside openSUSE LEAP 15.3?
Thanks in advance for replies.
While I understand why you have hung your question at the end of this thread, it is already old and bound to 15.1.
Better start a new thread, when needed with a link to this thread. It will show then in the list of new threads, with a good titles which will give you a much wider audience then hoping that someone still watches this old one.