majesty-diffusion VS tortoise-tts

You missed Majesty Diffusion. It's rather complicated to use because it uses latent space diffusion and CLIP guidance at the same time, so you have to get many settings right, but once you do it can give amazing results, go see them on their Discord!

Here are a couple I've used recently:

Majestic diffusion - https://github.com/multimodalart/majesty-diffusion

Centipede diffusion - https://colab.research.google.com/github/Zalring/Centipede_D...

I suck with computers so i hope these links mean something to you, looks like devil witch magic to me. link1 link2 link3

There's also another model going around called Latent Majesty Diffusion that does the same thing.

I found the github: https://github.com/multimodalart/majesty-diffusion

Check https://github.com/multimodalart/majesty-diffusion

There is a Google Colab workbook that you can try and run for free :)

This is the image-text pairs behind: https://laion.ai/laion-400-open-dataset/

GitHub repo.

I use Tortoise TTS. It's slow, a little clunky, and sometimes the output gets downright weird. But it's the best quality-oriented TTS I've found that I can run locally.

https://github.com/neonbjb/tortoise-tts

neonbjb/tortoise-tts

EDIT: It appears to be the exact same issue as this

It was primarily being used to train TTS models (see https://github.com/neonbjb/tortoise-tts), which largely fit into a single GPUs memory. So, for data parallelism, x8 PCIe isn't that much of a concern.

Previously TortoiseTTS was associated with PlayHT in some way, although the exact connection is a bit vague [0].

From the descriptions here it sounds a lot like AudioLM / SPEAR TTS / some of Meta's recent multilingual TTS approaches, although those models are not open source, sounds like PlayHT's approach is in a similar spirit. The discussion of "mel tokens" is closer to what I would call the classic TTS pipeline in many ways... PlayHT has generally been kind of closed about what they used, would be interesting to know more.

I assume the key factor here is high quality, emotive audio with good data cleaning processes. Probably not even a lot of data, at least in the scale of "a lot" in speech, e.g. ASR (millions of hours) or TTS (hundreds to thousands). As opposed to some radically new architectural piece never before seen in the literature, there are lots of really nice tools for emotive and expressive TTS buried in recent years of publications.

Tacotron 2 is perfectly capable of this type of stuff as well, as shown by Dessa [1] a few years ago (this writeup is a nice intro to TTS concepts). With the limit largely being, at some point you haven't heard certain phonetic sounds before in a voice, and need to do something to get plausible outcomes for new voices.

[0] Discussion here https://github.com/neonbjb/tortoise-tts/issues/182#issuecomm...

[1] https://medium.com/dessa-news/realtalk-how-it-works-94c1afda...

Tortoise GitHub repo - Source code, documentation, and usage guide

TorToiSe (https://github.com/neonbjb/tortoise-tts) produces the best quality speech of any freely available model. However, its long inference times makes it impractical for voice chatbots like Gdansk.