espnet VS tortoise-tts

You might check out this list from espnet. They list the different corpuses they use to train their models sorted by language and task (ASR, TTS etc):

https://github.com/espnet/espnet/blob/master/egs2/README.md

- https://github.com/espnet/espnet

This link has instructions for doing this for a Japanese model. It would have to be altered to work with ljspeech and the fine tune dataset.

This work is made possible by the excellent advancements in text to speech modeling. ESPnet is a great project and should be checked out for more advanced and a wider range of use cases. This pipeline was also made possible by the great work from espnet_onnx in building a framework to export models to ONNX.

CMU WavLab has ESPNet https://espnet.github.io/espnet/ which includes a number of high quality TTS models including VITS (which in my subjective experience is just as good as what is demonstrated here). Also the inference on various ESPNet pretrained TTS models is reasonable and sentences take on average 5 seconds per word to generate the waveform on my totally mid PC setup.

The reason I'm saying this is to point out that having and in-depth knowledge on speech processing/generation requires a lot of information about signal processing and human speech in general (eg. acoustics and phonetics). However, if you're not into learning everything there is to know about a subject, just take one state-of-the-art example and study that as best as you can. Pick one environment/toolkit, for example espnet and simply go with that.

https://github.com/espnet/espnet (kind of like a newer Kaldi, but also not beginner friendly)

both provide e2e ASR support but espnet does have more utilities where as speechbarain is clean

This is relatively small amount of speech to train the model from scratch, but you can train using another pre-trained model for initialization. There are numbers of end-to-end ASR toolkits which can be used for this: https://github.com/NVIDIA/NeMo and https://github.com/espnet/espnet

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.