Speech-to-image generation using Jina

The current generation of speech-to-text and image generation models are moving at a lightning pace, with models able to generate results that we couldn't have dreamed of a couple of years ago. But how can we use these models ourselves? And more importantly, is it possible to productionize them?

In this webinar, Alaeddine Abdessalem, Software Engineer at Jina, will show us how to use Whisper and StableDiffusion models and the Jina framework to develop an end-to-end multimodal application, capable of generating artwork from audio. He'll then show us how to deploy this application to Jina Cloud.

Speaker: Alaeddine Abdessalem

#jina #whisper #pycharm

Видео Speech-to-image generation using Jina канала PyCharm, a JetBrains IDE