Published on

AI Engineer Gemini Event

Presentation
Authors

The seventieth MeetUp of the Machine Learning Singapore Group, was titled : “AI Engineer Gemini Event” - and held at an earlier date in the month than usual because of the imminent arrival of AI Engineer in Singapore. Since Google was a sponsor for AI Engineer, MLSG offered to host the event with a focus on Gemini (and, as it turned out, Robotics too!).

My Presentation

My talk was titled “Something cool with TTS”. It had the following outline :

  • Gemini-TTS
    • Announcement
    • AI Studio playtime
    • Coding in Colab
    • Resources
  • How are TTS models trained?
    • Example Open Source model
    • Voice Cloning Colab
  • Wrap-up & QR-code

Slides

The slides for my talk, which contain links to all of the reference materials and sources, are here :

Presentation Screenshot

If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.

Presentation Screenshot

Other Presentations

The MeetUp also featured:

  • “Prototyping fast in Antigravity” - Ivan Leo

    • Ivan is from the Google DeepMind DevRel team, and was eager to tell us about Anti-Gravity.
    • Ivan has not experience quota issues, which is encouraging
  • “Robotics Planning with Gemini” - Chaitanya Jadhav & Anurag Roy

    • Anurag and Chaitanya demonstrated how Gemini’s multimodal and reasoning capabilities can power a pipeline that converts photos of an indoor space into a map and then generates executable task plans for robots with different embodiments.
  • “From Lab to Laundry: Scaling Robot Autonomy in the Real World” - Daniel Ng & Siddharth Krishnan

    • Daniel and Siddharth explained how teleoperation is likely to form a significant role in the practical build-up of robot systems
    • They even brought along robotic arms (and controllers) for the attendees to play with!

Acknowledgements

Many thanks to the Google team, who allowed us to use Google’s Developer Space, and generously provided food for our audience.