Speech to text -

[David Dembrow]

On 11/16/20 11:03 PM, [e-mail] wrote:
> Date: Mon, 16 Nov 2020 17:41:33 -0500
> From: Bob Goodwin
> Subject: Speech to text -
> To: Fedora List
> Message-ID:
> Content-Type: text/plain; charset=utf-8; format=flowed
>
> Is there a voice to text program that will work with Fedora Linux as
> some of my friends have for their smart phones? It would not have to be
> free to be considered.
>
> -- Bob Goodwin - Zuni, Virginia, USA FEDORA-32/64bit LINUX XFCE 
> Fastmail POP3 ------------------------------

I found something called festival installed on my fedora system that 
includes text to speech.  Package festival-2.5.0-13.fc33.x86_64.

[Bob Goodwin]

On 2020-11-17 10:18, David Dembrow wrote:
> I found something called festival installed on my fedora system that 
> includes text to speech.  Package festival-2.5.0-13.fc33.x86_64.

.
When I looked at Festival in the past that is all it did, one thing, 
conventioneer text to spoken English. I am referring to the application 
on smart phone that permits the user to dictate a message  and send it 
as text. I receive email messages created that way everyday from two 
people with android phones.

[stan]

On Tue, 17 Nov 2020 10:32:46 -0500
Bob Goodwin  wrote:
>                                   I am referring to the
>
> application on smart phone that permits the user to dictate a message
>  and send it as text. I receive email messages created that way
> everyday from two people with android phones.

https://fosspost.org/open-source-speech-recognition-2020/

https://www.ubuntupit.com/best-open-source-speech-recognition-tools-for-linu...

[Bob Goodwin]

On 2020-11-17 11:00, stan via users wrote:
> On Tue, 17 Nov 2020 10:32:46 -0500
> Bob Goodwin  wrote:
> >                                    I am referring to the
> >
> > application on smart phone that permits the user to dictate a message
> >   and send it as text. I receive email messages created that way
> > everyday from two people with android phones.
>
> https://fosspost.org/open-source-speech-recognition-2020/
>
> https://www.ubuntupit.com/best-open-source-speech-recognition-tools-for-linu...

.
The answer to my original question is no, there is nothing available to 
do what I asked, essentially to produce a text message by dictation. 
Actually someone had asked me if I could and I was not certain.

Thanks to all for the help,   Bob

[Andras Simon]

2020-11-17 22:05 UTC+01:00, Bob Goodwin :
> The answer to my original question is no, there is nothing available to
> do what I asked, essentially to produce a text message by dictation.

You asked for a voice to text program. Doesn't this fit the bill?

Name         : pocketsphinx
Epoch        : 1
Version      : 5
Release      : 0.3.prealpha.fc32
Architecture : x86_64
Size         : 42 k
Source       : pocketsphinx-5-0.3.prealpha.fc32.src.rpm
Repository   : updates
Summary      : Real-time speech recognition
URL          : http://cmusphinx.sourceforge.net/
License      : BSD
Description  : PocketSphinx is a version of the open-source Sphinx-II speech
             : recognition system which is able to recognize speech in
             : real-time.  While it may be somewhat less accurate than the
             : offline speech recognizers, it is lightweight enough to run on
             : handheld and embedded devices.

I haven't tried it, but the description suggests that perhaps you should.

Andras

[Bogdan Cristea]

You could have a look at ML algorithms published by AI researchers, e.g.

https://github.com/pytorch/fairseq/tree/master/examples/wav2vec https://github.com/pytorch/fairseq/tree/master/examples/wav2vec

But some additional work must be done in order to transform this into an application for speech to text.
> On 17 Nov 2020, at 23:13, Andras Simon  wrote:
>
> 2020-11-17 22:05 UTC+01:00, Bob Goodwin :
> > The answer to my original question is no, there is nothing available to
> > do what I asked, essentially to produce a text message by dictation.
>
> You asked for a voice to text program. Doesn't this fit the bill?
>
> Name         : pocketsphinx
> Epoch        : 1
> Version      : 5
> Release      : 0.3.prealpha.fc32
> Architecture : x86_64
> Size         : 42 k
> Source       : pocketsphinx-5-0.3.prealpha.fc32.src.rpm
> Repository   : updates
> Summary      : Real-time speech recognition
> URL          : http://cmusphinx.sourceforge.net/
> License      : BSD
> Description  : PocketSphinx is a version of the open-source Sphinx-II speech
>             : recognition system which is able to recognize speech in
>             : real-time.  While it may be somewhat less accurate than the
>             : offline speech recognizers, it is lightweight enough to run on
>             : handheld and embedded devices.
>
> I haven't tried it, but the description suggests that perhaps you should.
>
> Andras
> _______________________________________________
> users mailing list -- [e-mail]
> To unsubscribe send an email to [e-mail]
> Fedora Code of Conduct: https://docs.fedoraproject.org/en-US/project/code-of-conduct/
> List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines
> List Archives: https://lists.fedoraproject.org/archives/list/[e-mail]