MULTIMODAL AI

→ View original post on X — @reach_vb

Lithuanian Whisper Model Achieves Major WER Improvement

By

@reach_vb

–

15 December 2022 19h05

Lithuanian @DeividasMat
's fine-tuned Whisper medium checkpoint managed to get the WER down from 35.2 (large) -> 20.44 Model:

Combining Four AI Models for Advanced Video Generation

By

–

15 December 2022 18h30

It's http://
d-id.com's amazing tech behind it, so I'm now combining 4 different AI models to get this result (training, generating, outpainting and then making a video)

AI Video Avatars Now Live for Everyone

By

–

15 December 2022 18h28

✨ AI Video Avatars are now live on https://t.co/Hccng2Gk3t for everyonehttps://t.co/oNawvyxWS1
— @levelsio (@levelsio) 15 décembre 2022

AI Avatars are now live on http://
avatarai.me for everyone

AI Video Avatars Platform Launched for Personalized Video Creation

By

–

15 December 2022 18h27

✨ Launched AI Video Avatars @ https://t.co/Hccng2Gk3t

🎤 You can now transform any of the 120+ generated AI avatars into a talking video, with your voice or text which I'll text-to-speech for you

🎅 Maybe nice as a video Christmas card?

🫲 Manually for now to validate market https://t.co/hcizu0zcPZ pic.twitter.com/D2JOVsiDiV
— @levelsio (@levelsio) 15 décembre 2022

Launched AI Avatars @ http://
avatarai.me You can now transform any of the 120+ generated AI avatars into a talking video, with your voice or text which I'll text-to-speech for you Maybe nice as a video Christmas card? Manually for now to validate market

→ View original post on X — @cohere

Auto Diagram Creator: AI Tool with Creative Temperature Settings

By

@cohere

–

15 December 2022 15h49

Now with a higher temperature (1.0), we get an idea of an auto diagram creator. Definitely more ambitious!

→ View original post on X — @replicate

Harmonai joins Replicate with open source audio ML models

By

@replicate

–

15 December 2022 15h38

Also, welcome @harmonai_org to Replicate! They're a open source collective of audio ML hackers. This is just the first of many models they're working on and we're looking forward to all those robo-tunes.

→ View original post on X — @reach_vb

100K Model Milestone: Whisper Model Prediction

By

@reach_vb

–

15 December 2022 11h20

Bet the 100Kth model was a Whisper model

This House Does Not Exist Adds Image Upscaler Improves Performance

By

–

15 December 2022 4h34

Adding an upscaler to This House Does Not Exist now so the images get a bit more crispy and sped up page load from ~500ms to ~5ms https://
thishousedoesnotexist.org/beach?time=30d