@fastfinge

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@hosford42 In general, for training the rules for pronouncing English, the CMU pronouncing dictionary is used: www.speech.cs.cmu.edu/cgi-bin/cmudict

When it comes to open-source speech data, LJSpeech is the best we have, though far from perfect: keithito.com/LJ-Speech-Dataset/

And here's a link to GnuSpeech, the only open-source fully articulatory text to speech system I'm aware of: github.com/mym-br/gnuspeech_sa?tab=readme-ov-file

I'm afraid I don't have any particular data of my own.

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@hosford42 The sourcecode for dectalk is out there. Unfortunately, It's...legally dubious at best. It was leaked by an employee back in the day, and now the copyright status of the code is so unclear that nobody can safely use it for anything, but also nobody can demonstrate clear enough ownership to submit a DMCA and get it taken off github. GNUspeech is also pretty close to what's needed, but it won't even compile without all the NeXT development tools, I don't think. So at best all that would be is a base for something else; modernizing it would probably effectively be a complete rewrite anyway.

1

0

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@hosford42 The reason I say systems-level programming is mostly because for a text to speech system used by a blind power user, you need to keep an eye on performance. If the system crashes and the computer stops talking, the only choice the user has is to hard reset. It would be running and speaking the entire time the computer is in use, so memory leaks and other inefficiencies are going to add up extremely quickly.

From what I can tell, the ideal is some sort of formant-based vocal tract model. Espeak sort of does this, but only for the voiced sounds. Plosives are generated from modeling recorded speech, so sound weird and overly harsh to most users, and I suspect this is where most of the complaints about espeak come from. A neural network or other sort of machine learning model could be useful to discover the best parameters and run the model, but not for generating audio itself, I don't think. This is because most modern LLM-based neural network models can't allow changing of pitch, speed, etc, as all of that comes from the training data.

Secondly, the phonemizer needs to be reproducible. What if, say, it mispronounces "Hermione". With most modern text to speech systems, this is hard to fix; the output is not always the same for any given input. So a correction like "her my oh nee" might work in some circumstances, but not others, because how the model decides to pronounce words and where it puts the emphasis are just a black box. The state of the art, here, remains Eloquence. But it uses no machine learning at all, just hundreds of thousands of hand-coded rules and formants. But, of course, it's closed source (and as far as anyone can tell the source has actually been lost since the early 2000's), so goodness knows what all those rules are.

1

2

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@hosford42 Sadly, there is no money in solving any of my problems. If there was, someone would have solved them. See, for example, my complaints about text to speech systems. stuff.interfree.ca/2026/01/05/ai-tts-for-screenreaders.html

I can go into more detail about why all the options are bad if you want. But this is the sort of problem that eats years of your life, requires advanced mathematics (digital signal processing at a minimum), and advanced linguistics, on top of being a good systems-level programmer.

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@Tamasg Have you tried Gemini? I find it's the best for stuff where I don't know exactly what I want.

1

0

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@jscholes Maybe. I've played enough of this style of game that I have pretty strong opinions about how it should all work, though.

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@jscholes If I ever finish the basics, the thing I'm aiming for, probably in 70 years or so, is a singleplayer trade wars/elite style space game. Planetary exploration, trading, combat, procedurally generated galaxy, etc. All the stuff we have in that style is either multiplayer PVP, or only semi-accessible like smugglers5. Interface via console menus, because that feels both simple and retro. But with stuff happening in realtime like textspaced used to be (it's now discontinued), and high quality sound. The idea is you just let it run on your taskbar and check in every 20-30 minutes when you hear something that needs doing. So kind of casual all-day play while multitasking. I've dreamed of something like that for like 20 years, but nobody has done anything even close. Textspaced was the nearest, but it never quite got there, and it's gone, now.

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@jscholes Hah. So this all started when I decided I wanted a class where I could create a new menu, add the selection key, a name, and a callback function for each item, then call the menu to print itself and do all the input and error checking, and call the callback for whatever item was chosen. And then it just kept growing. I'm not even at the object graph stage. I just hate most of the text games I mentioned, where every menu looks and acts different, because print statements and case statements are just sprinkled all over the code.

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@jscholes If I do it that way, it just means refactoring later, though. And that's even harder and less fun because now you're rebuilding things that already exist.

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

Games I love like Warsim, The Wastes, and usurper inspired me to think about creating my own console-based game. Then I wrote 750 lines of code just to make a reusable system for console menus. And realized the save system is going to be another 500 lines, probably. And then the settings system. And after thinking about 2000 lines of code before I can get to anything even resembling the simplest game mechanic, I'm not inspired, anymore. Why is 99 percent of programming doing the least interesting part of any project?

2

3

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

I've only played a couple of minutes, but Usurper Reloaded looks really #accessible and like loads of fun. With all kinds of content for an alpha 0.1. I never played the original BBS #game, so I don't know how it compares. Run the .bat file to get the console version: github.com/binary-knight/usurper-reloaded/

1

2

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@clv1 @cachondo @Tamasg @jscholes @FreakyFwoof @pixelate @ZBennoui @amir And also UX researchers, probably. I can't articulate why eloquence is better than dectalk, for me. Neither, I bet, could Andre articulate what makes Orpheus better than Eloquence, for him. So to get something that makes the largest number of people as happy as possible is a classic UX research problem, probably involving massive surveys, rating and ranking of samples, and so on. I work with the kind of people qualified to do this, and it's a unique skill-set in and of itself.

0

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@MostlyBlindGamer But I'm not disappointed that the package description does nothing to explain why the package exists, why it's better, or why it should be used over the dozens of other ORM-like options.

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

You cannot just write "potato is being blocked on my laptop" as the subject of your support request, and then just leave it at that. I don't know, either. Knowing computer people though, there are probably seven different incompatible versions of potato, and "potato" could be anything from a word processor to a network diagnostic tool. You thought I was joking, huh? So did I! But googling for potato software reveals an AI tool for biologists, some kind of audio mixing tool, an instant messenger, a text annotation tool, a background transcription tool, and more. All of these programs are all called just "potato". Also, the AI answers above the search results happily tell me, with no context: "Start using potato in your project by running npm i potato. The children components of your potatoes may themselves have components and your potatoes might rapidly look like small tree-like structures of components." I'll...get right on that. Potatoes that look like trees and have children is the one thing all of my projects are missing!

1

4

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@NicksWorld This is exactly what the Germans said during world war II. If you don't believe Alligator Alcatraz, and the detention centers ICE is running in Honduras, are concentration camps, you are just like the germans who claimed they were "just following orders". Your president is actively planning an armed invasion of my country of Canada, so don't expect any simpathy from me. Let's hope there will eventually be an equivalent of Nuremberg trials, and all of you enabling the modern SS will also get the justice you deserve.

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@NicksWorld But I wouldn't be in ICE. This is the equal of Hitler's SS, and these people deserve exactly what the SS Officers got.

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@FreakyFwoof Shite.

1

0

1

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@rmcpantoja Also, I'd love to hear if and when you release anything!

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@jpellis2008 @FreakyFwoof Check the thread. It was found. :-)

0

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

9mo

@jscholes LOL nope. They were trying to age up the characters so the teen author wouldn't have to do historical research about what things were like in the 1980's, and could just give them all cell phones and have them listening to real music, rather than whatever medieval chanting they used to do in 1988.

2

0