Charles has mentioned that he can't used net-based solutions for speech-to-text for confidentiality reasons.
Privacy is definitely getting harder these days as developers for this kind of tool are looking to improve accuracy by using "machine learning" (aka industrial-level pattern matching) by using everyone's submitted material as new data to continue training the tool (and who knows what other purposes).
Older versions are probably the way to go where confidentiality is important. They may need a bit more prompting / occasional corrections, though, especially depending on accent.
Deborah
-----Original Message-----
From: Code for Libraries <[log in to unmask]> On Behalf Of Andrew Nagy
Sent: Tuesday, 13 December 2022 9:00 am
To: [log in to unmask]
Subject: Re: [CODE4LIB] Hiring a programmer
[You don't often get email from [log in to unmask] Learn why this is important at https://aka.ms/LearnAboutSenderIdentification ]
Caution: This email originated from outside our organisation. Do not click links or open attachments unless you recognize the sender and know the content is safe.
For #1, if you have some skills working with APIs, there are some great cloud-based Speech-To-Text solutions out there that you can easily use.
https://cloud.google.com/speech-to-text
https://aws.amazon.com/transcribe/
Both offer a "free tier" where if you only need to use the service a little bit, its free! But generally these services only charge a little per month if you go over the free limit. Its pay as you go with cloud services. If you don't have experience creating your own tools that make API calls, I'm sure you can find someone on this list who would be willing to help as a freelance project for $500 or less!
Nowadays you can find an API for just about anything that is cloud based and pay as you go.
Best of luck
Andrew
On Mon, Dec 12, 2022 at 2:28 PM Anne Slaughter < [log in to unmask]> wrote:
> Hi Charles,
>
> I agree with the perspectives you've received on the challenges of
> building and sustaining something yourself with the limited resources
> you describe, and that includes outsourcing what might seem like a
> one-time project for a low rate; it just isn't likely to deliver what
> you're ultimately looking to achieve, for too many depressing reasons
> to list. I wonder if you might be able to find some additional ideas
> for a voice-to-text solution if you reached out to other public
> libraries with makerspaces/production studios. Code4Lib folks are
> clearly awesome in many ways, but the public sector representation
> isn't extensive in this community, which in library software land can
> translate to big differences at almost all levels when you're trying
> to identify the right solution for your organization.
>
> For another angle, are you connected with the folks in the Library
> Development Group at the Florida State Library/FLIN (
> https://dos.myflorida.com/library-archives/library-development/digital
> /resource-sharing/flin/), or your local multitype cooperative (looks
> like it's this one:
> https://swfln.org/)? They might be able to connect you to vendor
> discounts, other folks working on the same issues, or other resources
> - and at the very least, the more they understand about your needs,
> the better they can plan their service offerings to help improve the
> libraries they serve.
>
> Anne Slaughter
> Director of Technology Services
> Reaching Across Illinois Library System Burr Ridge Office
> Phone: 630-734-5127
> Fax: 630.734.5050
> [log in to unmask]
> https://www.railslibraries.info
>
> -----Original Message-----
> From: Code for Libraries <[log in to unmask]> On Behalf Of
> charles meyer
> Sent: Saturday, December 10, 2022 4:29 PM
> To: [log in to unmask]
> Subject: Re: [CODE4LIB] Hiring a programmer
>
> Thank you Jackie, Erich, Mark Jon, Deborah and all others!
>
>
>
> 2 projects I’ve got on the back burner.
>
>
>
> 1 – since I can’t find any voice-to-text software other than DNS
> ($500) and don’t wish to use the Windows/Word voice-to-text or Google
> options, which others have used (not just Googled but actually used) I
> was curious what kind of price range it would be to hire a programmer
> to create a voice-to-text program?
>
>
> For confidentiality purposes, I can't be on the net for the voice-to-text.
>
>
>
> I’m not a software developer so I have no idea the actual costs and
> time involved in creating, developing and completing such a project.
> Maybe I need to wait for that winning lottery ticket?!
>
>
>
> 2 – I wanted to create or have created a short animated object. I’ve
> read about Blender but with no experience creating animation it was a
> slog to watch Blender tutorials and then try to develop what I wanted.
> It was easier (although certainly not easy) to learn the basics of
> some free video editing software.
>
>
>
> I then posted a request to see to if anyone might help me or I could
> hire on Blender but that was met with a thud.
>
>
>
> The vison I have for the animated object really needs to be in 3D and
> not 2D although I do respect how 2D can work well in some projects.
>
>
>
> Perhaps, if I wasn’t teaching 3D printing, doing video recording,
> running AV, doing video editing, creating writing programs, and doing
> all the other tasks needed in a public library I might have a little
> left over time to play with Blender but not so far.
>
>
>
> Thank you for all your thoughts and suggestions.
>
>
>
> Charles.
>
>
>
> Charles Meyer
>
> Charlotte County Public Library
>
>
________________________________
"The contents of this e-mail (including any attachments) may be confidential and/or subject to copyright. Any unauthorised use, distribution, or copying of the contents is expressly prohibited. If you have received this e-mail in error, please advise the sender by return e-mail or telephone and then delete this e-mail together with all attachments from your system."
|