nerd-dictation VS tortoise-tts

nerd-dictation

There's no built-in way of doing this in GNOME, but you might already get a bit further with tools like https://github.com/ideasman42/nerd-dictation

I'm not familiar with Talon so I don't know if this is a suitable suggestion but nerd-dictation seemed to have been well received here when it was last promoted and it looks like it's still in active development.

TBF Microsoft dropped IE, windows phone... that is not uncommon. But the OP is right, maybe not much for voice control but for dictation certainly. The FLOSS community is always far behind and thus always struggle with new technologies. We should be prepared. Since you've mentioned small open source project here's a demo of NerdDitaction. FYI Linux do have mobile devices developing.

Yeah you get me. I did have RSI which was amplified by my other issue, but it was that issue that progressed and why can't type now, not RSI. I'd be interested in hearing about using numen in combination with typing, but it's likely not ideal yet. Maybe just using speech to text for some things could help? It's not my project but there's: https://github.com/ideasman42/nerd-dictation that uses the same speech recognition as numen.

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.