Embarrassingly Easy E2 TTS Model from Microsoft

This video introduces E2 TTS (Embarrassingly Easy TTS) which is a fully non-autoregressive zero-shot text-to-speech (TTS) system capable of generating the voice of any speaker. Despite its extremely simple model architecture and training scheme, E2 TTS achieves human-level naturalness, and state-of-the-art speaker similarity and intelligibility.
🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahd...
🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon:
bit.ly/fahd-mirza
Coupon code: FahdMirza
▶ Become a Patron 🔥 - / fahdmirza
#e2tts
PLEASE FOLLOW ME:
▶ LinkedIn: / fahdmirza
▶ KZbin: / @fahdmirza
▶ Blog: www.fahdmirza.com
RELATED VIDEOS:
▶ Resource www.microsoft....
All rights reserved © 2021 Fahd Mirza

[@IdPreferNot1]

These,and OAI are just burning customer goodwill at this point with these demos.

[@fahdmirza]

yes they should have released it too.

[@timer4times2]

Then why t f does Microsoft show it then? All these AI companies love to tease and tease and no f release.

[@fahdmirza]

yeah , hopefully they will release it soon.

[@bassam5714]

just to tease, no release.

[@fahdmirza]

yeah , hopefully they will release it soon.

[@ojikutu]

E2 TTS is purely a research project. Currently, we have no plans to incorporate E2 TTS into a product or expand access to the public.

[@fahdmirza]

Yes thats right

[@user-qc3gc8jt1k]

Hi! Thanks. What are the supported languages?

[@fahdmirza]

English at the moment.

[@suren0401]

this is really cool

[@fahdmirza]

indeed