Why not use a struct of arrays? https://en.wikipedia.org/wiki/Data-oriented_design
Because then you'd be running a full speech to text model all the time, and an LLM any time any speech is detected.
How does this interact with DRM? Does ACR still work if HDCP is being used?
Why not use a struct of arrays? https://en.wikipedia.org/wiki/Data-oriented_design
Because then you'd be running a full speech to text model all the time, and an LLM any time any speech is detected.
How does this interact with DRM? Does ACR still work if HDCP is being used?