gRPC Message sizes

As a follow up to this thread - Inference Broken - Long Form Audio and gRPC max message sizes - #4 by shantanu1

We can and have tried using the streaming inference API, but that means we completely loose out on the benefits of Offline/Batch inference. Is there a workaround we could use? Send in 4MB chunks of audio? I’m not sure how that would affect, say, citrine’s attention mechanism.

Are we not expected to run long-form audio on Riva as a use case? I thought with attention-based models like citrinet that that’s where they would shine.

If such batch/offline processing is not supported (at least for files >4MB) or not a pipeline you intend on supporting then please let us know, as we’re looking for a platform to serve that purpose primarily, and Jarvis/Riva seemed like a good fit for exactly that.

We would appreciate some/any indication on what you guys have in mind for the future regarding this. Yes, for now, we can use the streaming inference, but that makes sense for us as a stand-in only if long-form transcripts are eventually possible. Streaming and offline aren’t interchangeable, for our purposes.

It also looks like Triton supports configuring larger message size [1] and most other inference/training platforms support exposing this gRPC config[2]. Can we talk to Triton directly?

  1. Increase the GRPC client maximum message size. On infer request error… · triton-inference-server/server@e9b541b · GitHub
  2. Increasing the Maximum Message Size for gRPC — seldon-core documentation

Hey it looks like we’re receiving a standard response when it comes to inference on larger files - Jarvis ASR batch mode file size exceeds - #2 by SunilJB

Is it okay for us to ask for some transparency, at least in relation to whether the intention is to support larger files or not eventually? Would help us know what Riva aims to provide in terms of functionality and supported use cases. Right now we’d have to reevaluate because we simply don’t know if we’d be trying to get Riva to work in a non-primary use case down the line. If we were given this information or given some idea of the roadmap, it would help us make these decisions much better.

Hi @shantanu1 ,
Have responded to the original thread.