Hard to hold that line when you see who they are stealing from. Faggot worked for palantir and blackrock before that. I'm not gonna try to shit on anyone that paid for this, but i'm not gonna get too upset at anyone that tries to steal it from these people.
It's been brought up before, but Tortoise is slowly getting there - in just a week it's gotten more development for the Web UI that Stable Diffusion uses. It's still pretty rough - audio can be hit or miss, though I've had better luck creating a sample that's a minute long and using that opposed to multiple files. It cannot do walls of text, you have to break it down to one-two sentences and even then it may or may not result in what you want. Can be frustrating given how long they take to generate but some things I've fed through have been damn good clones.
Wish i wasn't a AMD user, would like to try out the newest developments on Tortoise, hope we get something everyone can use eventually. For me i find about 1 minute and 30 seconds works well but i still get horrific garbled speech more often than not using the Hugging Face space.It's been brought up before, but Tortoise is slowly getting there - in just a week it's gotten more development for the Web UI that Stable Diffusion uses. It's still pretty rough - audio can be hit or miss, though I've had better luck creating a sample that's a minute long and using that opposed to multiple files. It cannot do walls of text, you have to break it down to one-two sentences and even then it may or may not result in what you want. Can be frustrating given how long they take to generate but some things I've fed through have been damn good clones.
Stable Diffusion has seen a huge leap in quality so here's hoping Tortoise sees some development that starts pushing it towards that direction as well.
AI Voice Cloning
This repo/rentry aims to serve as both a foolproof guide for setting up AI voice cloning tools for legitimate, local use on Windows/Linux, as well as a stepping stone for anons that genuinely want to play around with TorToiSe. Similar to my own findings for Stable Diffusion image generation, this...rentry.org
Where can I read about this? I tried searching for it but couldn't find anything besides those clips made for boomers that go "I'm Biden, haha, you thought this was real? See? AI is the future!"
Deepfake technology and its consequences will be a disaster for the human race... however the memes are
It's unstable even for nvidia. Keeps telling me CUDA is unavailable. Nigger, I used it just ten minutes ago on another ML program.
It's been brought up before, but Tortoise is slowly getting there - in just a week it's gotten more development for the Web UI that Stable Diffusion uses. It's still pretty rough - audio can be hit or miss, though I've had better luck creating a sample that's a minute long and using that opposed to multiple files. It cannot do walls of text, you have to break it down to one-two sentences and even then it may or may not result in what you want. Can be frustrating given how long they take to generate but some things I've fed through have been damn good clones.
Stable Diffusion has seen a huge leap in quality so here's hoping Tortoise sees some development that starts pushing it towards that direction as well.
AI Voice Cloning
This repo/rentry aims to serve as both a foolproof guide for setting up AI voice cloning tools for legitimate, local use on Windows/Linux, as well as a stepping stone for anons that genuinely want to play around with TorToiSe. Similar to my own findings for Stable Diffusion image generation, this...rentry.org
It seems to work pretty well and has the added benefit of not being lobotomized and absolutely fuckered. While it isn't perfect, it's a step in the right direction. From what I've managed to dig up, elevenlabs uses tortoise with some closed-source modifications so the foundation is there.It's been brought up before, but Tortoise is slowly getting there - in just a week it's gotten more development for the Web UI that Stable Diffusion uses. It's still pretty rough - audio can be hit or miss, though I've had better luck creating a sample that's a minute long and using that opposed to multiple files. It cannot do walls of text, you have to break it down to one-two sentences and even then it may or may not result in what you want. Can be frustrating given how long they take to generate but some things I've fed through have been damn good clones.
Stable Diffusion has seen a huge leap in quality so here's hoping Tortoise sees some development that starts pushing it towards that direction as well.
AI Voice Cloning
This repo/rentry aims to serve as both a foolproof guide for setting up AI voice cloning tools for legitimate, local use on Windows/Linux, as well as a stepping stone for anons that genuinely want to play around with TorToiSe. Similar to my own findings for Stable Diffusion image generation, this...rentry.org
