Weekly round-up: Deploy OpenAI Whisper instantly

Deploy OpenAI Whisper instantly

We added Whisper, a best-in-class speech-to-text model, to our library of pre-trained models. That means you can deploy Whisper instantly on your Baseten account and build applications powered by the most sophisticated transcription model available.

You can deploy Whisper from its model page in the Baseten app. Just sign in or create an account and click “Deploy.” The model and associated starter app will be added to your workspace instantly.

Review improved model logs

In a comprehensive overhaul, we made model logs ten times shorter but way more useful. Here’s what we changed:

  • Build logs are now separated into steps for easier skimming
  • Model deployment logs are surfaced just like build logs
  • Model OOMs are now reported
  • Many extraneous log statements have been deleted

OOM logging is a particularly important improvement. An OOM, or out-of-memory error, is a special lifecycle event that we monitor for on Kubernetes. This error means that the model is too big for the infrastructure provisioned for it. Existing logging solutions don’t capture these errors, resulting in frustrating debugging sessions, so we built a special listener to let you know about OOMs right away.

1 Like

Thanks for this. I tried to work on the starter application to pass on a url via text input component. This gives me an error. Similar issues when using the file picker component. Is there a way to identify what’s causing it?

Component:button2,Event:On click run worklet,Error:❌ Node "Invoke Model" failed (ModelServingError): Failed to invoke model version 6wgo9j3.

Worklet name:Worklet1,Status:FAILED,env:{},inputData:{"url":"selectedAudioUrl"},output:{},Scheduled:NO,Worklet ID:RqgrAQP,Run ID:qQWAONN,Latency (ms):107

2 Likes

oh no! I’m so sorry you’ve run into an issue - I’ll pass this along to our team and see what I can find out!

1 Like

Hey Ashish, thanks for looking to extend on the starter app – just looking at the error logs you shared it seems to me that the audio url that you are passing to the model invoker worklet isn’t formatted correctly. Your application should work if you wrap the file picker url or the text input url in curly braces. (i.e. the url param passed to the worklet should be bound to {{AudioURL.value}}) Hope that helps!

2 Likes