HackerTrans
TopNewTrendsCommentsPastAskShowJobs

ZDisket

no profile record

Submissions

Show HN: Real-time local TTS (31M params, 5.6x CPU, voice cloning, ONNX)

github.com
4 points·by ZDisket·4 miesiące temu·4 comments

comments

ZDisket
·4 miesiące temu·discuss
Yes. Specifically, the pipeline is text -> phonemizer -> phonemized text -> TTS model -> audio You just have to modify the phonemizer's dictionary.
ZDisket
·4 miesiące temu·discuss
No multilingual capabilities yet, although that is planned for next iteration.
ZDisket
·4 miesiące temu·discuss
I'll explain in detail once I've got the big release, but everything's been thoroughly modernized. Transformer, HiFi-GAN (now iSTFTNet w/Snake) vocoder, et al, plus a few additions.
ZDisket
·4 miesiące temu·discuss
Multilingual and local? Try out Supertonic 2.
ZDisket
·4 miesiące temu·discuss
I'm working on a voice cloning version of my TTS model, a highly upgraded VITS:

https://x.com/ZDi____/status/2013655958027669958

Right now, I only have single speaker checkpoints (as per the old video). That will change soon.
ZDisket
·4 miesiące temu·discuss
Upwork has candidates buy "connects" with real money that are spent when applying to jobs. Ultimately it seems some form of payment is a proven gate.