Skip to main content

Exciting news on open-source neural voices!
Our first experiment is complete with fantastic results! Check out the audio sample attached to this post.
For this month, @pneumasolutions provided GPU resources for training. I really appreciate their contribution.
This is just the beginning. To keep training going, I'm still accepting donations. Any amount helps.
I'm happy to receive your donations via PayPal:
paypal.me/geotts
Please mention mush42/tts in the notes.
#SpeechSynthesis #AI #ML


Zaplaťte uživateli Beka Gozalishvili pomocí služby PayPal.Me

Přejděte na adresu paypal.me/geotts a zadejte částku. Protože jde o PayPal, je to jednoduché a bezpečné. Nemáte účet PayPal? Nevadí.
PayPal.Me
#AI #ML #speechsynthesis @Pneuma Solutions

Matt Campbell reshared this.

in reply to Musharraf

Lino Morales
Lino Morales
• •
QWow that sounds way better. I hope to see this working with NVDA in the future.
in reply to Musharraf

the esoteric programmer
the esoteric programmer
• •
does this use piper, or something else? it sounds a bit flatter than other piper voices
in reply to the esoteric programmer

Musharraf
Musharraf
• •
@esoteric_programmer
It uses OptiSpeech, developed by me based on recent advances in neural TTS technology.
Piper is based on Vits, which dates back to 2021.
github.com/mush42/optispeech/

GitHub - mush42/optispeech: A lightweight end-to-end text-to-speech model

A lightweight end-to-end text-to-speech model. Contribute to mush42/optispeech development by creating an account on GitHub.
GitHub
@the esoteric programmer
in reply to Musharraf

the esoteric programmer
the esoteric programmer
• •
is that capable of working in low resource environments? would the resulting thing be able to generate samples at a speed good enough for most screenreader use? or, is this not ment for that use case?
in reply to the esoteric programmer

Musharraf
Musharraf
• •
@esoteric_programmer
The model is designed from the ground up to be used with a screen reader running on the CPU.
It takes a lot of experimentation to strike the right balance between model efficiency and output quality. But I'm getting there!
@the esoteric programmer
in reply to Musharraf

spacedoggy
spacedoggy
• •
wow it sounds so much better than vits! It sounds like it's not even based on hifigan stuff
in reply to spacedoggy

Musharraf
Musharraf
• •
@spacepup
It is not based on Vits.
While the underlying repo supports multiple model architectures, this particular run is based on ConvNeXt-TTS architecture:
ieeexplore.ieee.org/document/1…

Convnext-TTS And Convnext-VC: Convnext-Based Fast End-To-End Sequence-To-Sequence Text-To-Speech And Voice Conversion

End-to-end (E2E) sequence-to-sequence (S2S) neural text-to-speech (TTS) models and E2E-S2S neural voice conversion (VC) models can achieve high-quality speech synthesis with a single neural network.
ieeexplore.ieee.org
@spacedoggy
in reply to Musharraf

spacedoggy
spacedoggy
• •
may i have a link to your optispeech hfc female checkpoint? I'd like to test this, i am really intreagued
in reply to spacedoggy

Musharraf
Musharraf
• •
@spacepup
Glad to hear this!
For now, I'm not making checkpoints available due to them being unstable.
While initial results are promising, I discovered an issue with FFT parameters. Fixed it, and currently waiting for the server to become available to fine-tune with corrected data.
Upon getting consistent output quality, I'll publish an online demo, and make the pretrained checkpoints available via HuggingFace.
@spacedoggy
⇧