2️⃣SignGemma is a sign language understanding model that’s coming later this year 🤟🏼It’s a massively multilingual model that’s best at translating ASL into English text, enabling further development of tech access for Deaf and Hard of Hearing users. 🧏 Share your feedback and interest in early testing here:

We’re excited to share about MedGemma, SignGemma, and DolphinGemma 🧵↓

1️⃣MedGemma is a new collection of Gemma 3 variants created to accelerate the development of medical text and image applications, such as analyzing medical images or clinical reasoning.

MedGemma's 4B (multimodal) and 27B (text-reasoning) models offer strong performance for medical text/image comprehension, making them adaptable across medical applications. MedGemma runs efficiently on a single GPU for fine-tuning and inference, giving you full health data control thanks to its open nature.

3️⃣DolphinGemma can generate new synthetic dolphin sounds, which may one day make interspecies communication possible. More than 40 years of dolphin vocalization research has been leveraged to create the LLM. Dive into the story behind this FIN-tastic model.

This unlocks the possibility of developers coding with arcane hand symbols and gestures; which will be hilarious. I think that the future looks good for techno-wizardry 🧙‍♂️

Will this eventually be symmetrical i.e. text-->ASL-->text or even voice-->ASL-->voice ?

It would be cool to see the lip tracking used for lip reading.

This is insane

SignGemma's multilingual prowess is a leap for accessibility! As a tech enthusiast, this sets new standards in inclusion. Ready to contribute and watch its evolution. device did my watch

@tetahh__

Excellent development, can hand hold physically challenged and make them interact with all in the new AI race...

I signed up for SignGemma a week ago, when are we expecting to hear back about the release of the model?