Technical forums » Speech recognition »
Pages in topic:   < [1 2 3 4 5] >
Is OpenAI’s Whisper better than Dragon?
Thread poster: Hans Lenting
Dan Lucas
Dan Lucas  Identity Verified
United Kingdom
Local time: 15:00
Member (2014)
Japanese to English
Lack of clarity Jan 24

Milan Condak wrote:
https://github.com/Dadangdut33/Speech-Translate/releases

See, I know you mean well, but this the sort of thing I struggle with. Why this URL? To what does it link? Is this official Talon downloads, and if not, why not? Not Talon but something else maybe, but in that case, again, why?

There is zero context. Unless I set aside some time for a deep dive on this it's just so opaque.
And I'm a techy sort.

Dan

[Edited at 2024-01-24 20:09 GMT]
 
Milan Condak
Milan Condak  Identity Verified
Local time: 16:00
English to Czech
There are different tools to use Whisper models Jan 24

Dan Lucas wrote:

Milan Condak wrote:
https://github.com/Dadangdut33/Speech-Translate/releases

Why this URL? To what does it link? Is this official Talon downloads, and if not, why not? Not Talon but something else maybe, but in that case, again, why?

There is zero context. Unless I set aside some time for a deep dive on this it's just so opaque.
And I'm a techy sort.

Dan


Michael Beijer is using Talon.
I was using Buzz, SubtitleEdit and now I am using Speech Translate.
Each SW is developed. There are old, newer a recent releases. They have different features. This is a main reason I always use Portable version without installation. I do not use Speech Translate for dictate into CAT.

Milan

Dan Lucas
 
Michael Beijer
Michael Beijer  Identity Verified
United Kingdom
Local time: 15:00
Member (2009)
Dutch to English
+ ...
example of using Talon-AI-Tools + Talon to use ChatGPT by voice Jan 25

here's a little example (not my own!) of what can be achieved using "Talon-AI-Tools" (https://github.com/C-Loftus/talon-ai-tools ) alongside Talon

https://1drv.ms/v/s!ApO4sBug0LBmgaLtY4y6IMqimQVmPgc?e=2DhAm1

Dan Lucas
 
Dan Lucas
Dan Lucas  Identity Verified
United Kingdom
Local time: 15:00
Member (2014)
Japanese to English
Impressive Jan 25

Michael Beijer wrote:
https://1drv.ms/v/s!ApO4sBug0LBmgaLtY4y6IMqimQVmPgc?e=2DhAm1

Thanks for that, was having difficulties with the slack URL posted earlier in the thread.

Dan
 
Michael Beijer
Michael Beijer  Identity Verified
United Kingdom
Local time: 15:00
Member (2009)
Dutch to English
+ ...
wow, it's super easy to add customized terminology (additional_words.csv) Jan 25

Just say "customize additional words" and a file called ‘additional_words.csv’ pops open:

additional_words.csv-adding

I just added the last two entries, which now work flawlessly!

I suppose I should change "Beijer,buyer" to "Michael Beijer,Michael buyer". Otherwise, every time I want to say "buyer", Talo will print "Beijer".

Part of the beauty of Talon is that it is all just text files and Python code, so it's super easy to edit stuff. Very much unlike Dragon, where everything is hidden in all kinds of legacy Windows crap.
 
Dan Lucas
Dan Lucas  Identity Verified
United Kingdom
Local time: 15:00
Member (2014)
Japanese to English
No dictation yet Jan 25

Can't even get it to spit out text using "say good morning" or some such.
Obviously I need to look at this a bit more closely.
(Which is what I was afraid of.)

Dan
 
Michael Beijer
Michael Beijer  Identity Verified
United Kingdom
Local time: 15:00
Member (2009)
Dutch to English
+ ...
2 questions Jan 25

Dan Lucas wrote:

Can't even get it to spit out text using "say good morning" or some such.
Obviously I need to look at this a bit more closely.
(Which is what I was afraid of.)

Dan


Hmm.

Have you already installed the ‘Community’ command set in your Talon user folder?

Literally just stick the whole (unzipped) folder downloaded from "https://github.com/talonhub/community" @
"C:\Users\[USERNAME]\AppData\Roaming\talon\user\community"

Also, are you running the free version or the beta?
 
Dan Lucas
Dan Lucas  Identity Verified
United Kingdom
Local time: 15:00
Member (2014)
Japanese to English
. Jan 25

Michael Beijer wrote:
Have you already installed the ‘Community’ command set in your Talon user folder?

Literally just stick the whole (unzipped) folder downloaded from "https://github.com/talonhub/community" @
"C:\Users\[USERNAME]\AppData\Roaming\talon\user\community"
Also, are you running the free version or the beta?

(1) I think the former: it says 0.4.0. (2) I accidentally cloned the community repo into the wrong folder and I'm still trying to work out how to undo that in git...

Dan
 
Michael Beijer
Michael Beijer  Identity Verified
United Kingdom
Local time: 15:00
Member (2009)
Dutch to English
+ ...
To Git or not to Git, ... Jan 25

Dan Lucas wrote:

Michael Beijer wrote:
Have you already installed the ‘Community’ command set in your Talon user folder?

Literally just stick the whole (unzipped) folder downloaded from "https://github.com/talonhub/community" @
"C:\Users\[USERNAME]\AppData\Roaming\talon\user\community"
Also, are you running the free version or the beta?

(1) I think the former: it says 0.4.0. (2) I accidentally cloned the community repo into the wrong folder and I'm still trying to work out how to undo that in git...

Dan


Ha ha, I tried to figure Git out once or twice, but always just end up downloading the zip and sticking it there manually.
 
Dan Lucas
Dan Lucas  Identity Verified
United Kingdom
Local time: 15:00
Member (2014)
Japanese to English
Nothing Jan 26

Michael Beijer wrote:
Have you already installed the ‘Community’ command set in your Talon user folder?

"community" now installed, mike set to the table mike, speech recognition engine set to Conformer D, and is "Enabled (awake)". No response to anything I say, e.g. "help active".

Any ideas what to try next?

Dan
 
Michael Beijer
Michael Beijer  Identity Verified
United Kingdom
Local time: 15:00
Member (2009)
Dutch to English
+ ...
hmm Jan 26

Dan Lucas wrote:

Michael Beijer wrote:
Have you already installed the ‘Community’ command set in your Talon user folder?

"community" now installed, mike set to the table mike, speech recognition engine set to Conformer D, and is "Enabled (awake)". No response to anything I say, e.g. "help active".

Any ideas what to try next?

Dan


The first thing I would do is probably activate the log viewer, from: Scripting > View Log

activate-View-Log

activate-View-Log2

Have a look and see if you can figure it out yourself. If not, hop on Slack and ask the developer. I remember having an issue at the beginning as well and Ryan asked to see my log file, which is @ C:\Users\[USER]\AppData\Roaming\talon\talon.log.

PS: as you can see from my log file, I'm not even using such a good microphone anymore. I'm getting perfect dictation/commands from a Logitech webcam (BRIO) mic.
 
Dan Lucas
Dan Lucas  Identity Verified
United Kingdom
Local time: 15:00
Member (2014)
Japanese to English
Put community directory in users... Jan 26

Dan Lucas wrote:
Any ideas what to try next?

Sorry, user error on my part. I did not have the "community" folder in the "user" folder.
It's working now.

Dan
 
Dan Lucas
Dan Lucas  Identity Verified
United Kingdom
Local time: 15:00
Member (2014)
Japanese to English
Training Jan 26

Michael Beijer wrote:
PS: as you can see from my log file, I'm not even using such a good microphone anymore. I'm getting perfect dictation/commands from a Logitech webcam (BRIO) mic.

Is there a training process for your own voice? I am getting good but not fantastic results so far, and I will have to find workarounds for the things that you cannot do such as select and say, so overall it is feeling a bit clumsy at this point but of course I have only been using it for twenty minutes.

Dan
 
Dan Lucas
Dan Lucas  Identity Verified
United Kingdom
Local time: 15:00
Member (2014)
Japanese to English
Feels a lot quicker than Dragon Jan 26

Very sprightly.

Dan
 
Michael Beijer
Michael Beijer  Identity Verified
United Kingdom
Local time: 15:00
Member (2009)
Dutch to English
+ ...
new hybrid engine is better (only available in the beta) Jan 26

Dan Lucas wrote:

Michael Beijer wrote:
PS: as you can see from my log file, I'm not even using such a good microphone anymore. I'm getting perfect dictation/commands from a Logitech webcam (BRIO) mic.

Is there a training process for your own voice? I am getting good but not fantastic results so far, and I will have to find workarounds for the things that you cannot do such as select and say, so overall it is feeling a bit clumsy at this point but of course I have only been using it for twenty minutes.

Dan


As far as I know there isn't a training process. Are you using the beta yet? As far as I know the new hybrid engine (which is only available in the beta) is better than the one in the free edition.

Dan Lucas
 
Pages in topic:   < [1 2 3 4 5] >


To report site rules violations or get help, contact a site moderator:

Moderator(s) of this forum
Peter Zauner[Call to this topic]
Prachya Mruetusatorn[Call to this topic]

You can also contact site staff by submitting a support request »

Is OpenAI’s Whisper better than Dragon?






Trados Studio 2022 Freelance
The leading translation software used by over 270,000 translators.

Designed with your feedback in mind, Trados Studio 2022 delivers an unrivalled, powerful desktop and cloud solution, empowering you to work in the most efficient and cost-effective way.

More info »
Protemos translation business management system
Create your account in minutes, and start working! 3-month trial for agencies, and free for freelancers!

The system lets you keep client/vendor database, with contacts and rates, manage projects and assign jobs to vendors, issue invoices, track payments, store and manage project files, generate business reports on turnover profit per client/manager etc.

More info »