piefed.nullspacedamnthefilibuster, damnthefilibuster@lemmy.world
Instance: lemmy.world
Joined: 3 years ago
Posts: 2
Comments: 179
Posts and Comments by damnthefilibuster, damnthefilibuster@lemmy.world
c/selfhosted
c/steamdeckComments by damnthefilibuster, damnthefilibuster@lemmy.world
CanadaWhat a dickhead.
European Graphic Novels++The names do. I was just lazy to go back and check. 😆
Ask LemmyYes, but…
The reason why iOS asks you to read specific things out loud is because of a thing called alignment - basically, it needs to map exactly sounds to exact phonemes. So if it’s making you say “apple”, it’s recording how you say “ae”, “puh”, and “l”.
When you expect it to take any random file, it needs to know specific things like, what’s the text, what is the time frame, when did the speaker speak in a normal voice vs a higher pitch or speed voice. Taking all of this information and created a voice is called “forced alignment” and that’s a field that’s well studied but not implemented on mobile phones as yet.
An alternative for you, if you want, say, Snoop Dog to be your Siri voice, is to actually use an AI generated Snoop Dog voice to say all the things that the Personal Voice feature expects and just play them out loud from your computer when setting up Personal voice. This assumes you use one of the many paid Snoop Dog AI voice companies out there.
Another way to get the voice you want is to just take a recording of someone, write the text of what they said and then feed it to a tool like the Gentle Forced Aligner - https://github.com/strob/gentle
This will give you enough material to then take it to AWS or Microsoft’s AI voice creator tools to create an AI voice. Then you can use that AI voice to say the same things that iOS Personal Voice wants you to say and again, play the correct recording when activating Personal Voice.
All of this assumes that is your end goal - Snoop Dogg as your Siri. Anything else, please let me know and I’ll help you with what you’re trying to achieve.
Yes that’s the one! And the way it starts is just so funny!
Oh you run EuroGraphic Novels? I just found that today! Thank you for Tintin Tuesdays. Just such a star, that fella!
Wooooow. Such diligence!
Interesting artwork.
By the way, have you seen the comic Ménage a Trois?
Who is the bitch in your commentary, OP?
There’s sex in Oglaf? I read it for the story!
/s
NonCredibleDefenseI like the TATA bit 😆
Compounding fines please! And per instance sold. If the fine doesn’t touch 1 Billion CAD then it won’t change things.
Wow, this artwork reminds me of Oglaf!
Science Memes
pics
Comic Strips@lemmy.world
They told Claude code to build it.
I was gonna say… OP much better rich to afford Photoshop!
No Stupid QuestionsYouTube costs, what, $25 per month to not show ads?
I reckon Facebook and instagram would be in the same range.
Today I LearnedRemind me what SBF did…
xkcd
Comic Strips@lemmy.world
Be so funny if the next scene is all these baddies running away because it’s IP Man and Bruce Lee who were coming in.
Yarrrrr.
What a dickhead.
The names do. I was just lazy to go back and check. 😆
Yes, but…
The reason why iOS asks you to read specific things out loud is because of a thing called alignment - basically, it needs to map exactly sounds to exact phonemes. So if it’s making you say “apple”, it’s recording how you say “ae”, “puh”, and “l”.
When you expect it to take any random file, it needs to know specific things like, what’s the text, what is the time frame, when did the speaker speak in a normal voice vs a higher pitch or speed voice. Taking all of this information and created a voice is called “forced alignment” and that’s a field that’s well studied but not implemented on mobile phones as yet.
An alternative for you, if you want, say, Snoop Dog to be your Siri voice, is to actually use an AI generated Snoop Dog voice to say all the things that the Personal Voice feature expects and just play them out loud from your computer when setting up Personal voice. This assumes you use one of the many paid Snoop Dog AI voice companies out there.
Another way to get the voice you want is to just take a recording of someone, write the text of what they said and then feed it to a tool like the Gentle Forced Aligner - https://github.com/strob/gentle
This will give you enough material to then take it to AWS or Microsoft’s AI voice creator tools to create an AI voice. Then you can use that AI voice to say the same things that iOS Personal Voice wants you to say and again, play the correct recording when activating Personal Voice.
All of this assumes that is your end goal - Snoop Dogg as your Siri. Anything else, please let me know and I’ll help you with what you’re trying to achieve.
Yes that’s the one! And the way it starts is just so funny!
Oh you run EuroGraphic Novels? I just found that today! Thank you for Tintin Tuesdays. Just such a star, that fella!
Wooooow. Such diligence!
Interesting artwork.
By the way, have you seen the comic Ménage a Trois?
Who is the bitch in your commentary, OP?
There’s sex in Oglaf? I read it for the story!
/s
I like the TATA bit 😆
Compounding fines please! And per instance sold. If the fine doesn’t touch 1 Billion CAD then it won’t change things.
Wow, this artwork reminds me of Oglaf!
Fucking Seattle.
Reminds me of that game Townscaper.
They told Claude code to build it.
I was gonna say… OP much better rich to afford Photoshop!
YouTube costs, what, $25 per month to not show ads?
I reckon Facebook and instagram would be in the same range.
Remind me what SBF did…
Boat mode!!!!
Be so funny if the next scene is all these baddies running away because it’s IP Man and Bruce Lee who were coming in.
Yarrrrr.